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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8165
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    752
    +0.08
    0.5%
    20
    +0.07
    0.5%
    314
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.08
    0.06
    22
    +0.07
    0.06
    123
    +0.07
    0.05
    Negative Logits
    ="#
    -0.55
    ctors
    -0.53
    BuyableInstoreAndOnline
    -0.50
    iterator
    -0.45
    CDC
    -0.45
    SourceFile
    -0.45
    UFF
    -0.44
    Generic
    -0.44
    ]}
    -0.44
     retard
    -0.44
    POSITIVE LOGITS
    pired
    0.55
    ked
    0.55
    been
    0.53
    anium
    0.50
    mology
    0.50
    stood
    0.49
    ul
    0.46
     abundance
    0.46
    iders
    0.45
     purse
    0.45
    Activations Density 0.742%

    No Known Activations