© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5647
    Prev
    Next
    INDEX
    Explanations

    information related to people's movements, particularly regarding changes in location or position

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.27
    0.9%
    608
    +0.20
    0.7%
    640
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.27
    0.13
    665
    +0.20
    0.11
    104
    +0.18
    0.07
    Negative Logits
     fooled
    -1.02
    ILY
    -1.01
     ramifications
    -0.97
     abducted
    -0.96
    spir
    -0.95
    RF
    -0.94
     nodd
    -0.94
     payable
    -0.91
    soever
    -0.91
     swayed
    -0.91
    POSITIVE LOGITS
     appease
    1.10
    ggles
    1.09
     accommodate
    1.08
     eliminate
    1.05
    Ct
    1.05
     minimize
    1.04
    raviolet
    1.04
     improve
    1.03
     grips
    1.03
     prioritize
    1.02
    Activations Density 1.784%

    No Known Activations