© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 39760
    Prev
    Next
    INDEX
    Explanations

    numeric values embedded in text-related data such as financial figures, statistics, and coding elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    711
    +0.13
    0.6%
    570
    +0.11
    0.5%
    165
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.13
    -0.01
    176
    +0.11
    0.04
    640
    +0.10
    0.38
    Negative Logits
    Ö¼
    -0.88
    heit
    -0.70
    hyde
    -0.69
    utsche
    -0.67
     Maur
    -0.65
    aution
    -0.64
    ctive
    -0.64
    cription
    -0.62
    eanor
    -0.61
    rimination
    -0.61
    POSITIVE LOGITS
     litter
    0.70
     Porn
    0.63
    ãģ®éŃĶ
    0.60
     punch
    0.60
    MSN
    0.59
    Dad
    0.59
     fists
    0.58
     Clippers
    0.58
    66666666
    0.56
     srfAttach
    0.56
    Activations Density 36.394%

    No Known Activations