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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3688
    Prev
    Next
    INDEX
    Explanations

    topics related to different categories or fields of knowledge

    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
    494
    +0.16
    0.5%
    655
    +0.15
    0.5%
    146
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.16
    0.06
    146
    +0.15
    0.06
    284
    +0.14
    0.06
    Negative Logits
    */(
    -1.30
     craw
    -1.14
    ibaba
    -1.05
     partName
    -1.04
     sidewalks
    -1.03
     edges
    -1.02
     perman
    -0.98
     leash
    -0.98
     arteries
    -0.98
    anchester
    -0.95
    POSITIVE LOGITS
    Zen
    1.22
    enza
    1.19
    EMENT
    1.18
     Spoiler
    1.16
    Weather
    1.10
    ulture
    1.09
    ement
    1.08
    anto
    1.08
    Plot
    1.06
    eta
    1.06
    Activations Density 1.216%

    No Known Activations