© 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. 3790
    Prev
    Next
    INDEX
    Explanations

    detailed historical and informative text, potentially related to politics and research

    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
    314
    +0.07
    0.5%
    572
    +0.07
    0.5%
    612
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.07
    0.12
    572
    +0.07
    0.11
    393
    +0.07
    0.22
    Negative Logits
    yss
    -0.41
     reciproc
    -0.41
     TRANS
    -0.41
    icable
    -0.40
     escalate
    -0.39
    escal
    -0.39
     routines
    -0.39
     GO
    -0.38
     horizont
    -0.38
     payoff
    -0.37
    POSITIVE LOGITS
    ãĥĥãĥī
    0.45
     Mechdragon
    0.44
    £ı
    0.43
    tm
    0.43
    pron
    0.43
     nutshell
    0.43
     Skies
    0.42
    */(
    0.42
     kidding
    0.42
    Mesh
    0.41
    Activations Density 7.976%

    No Known Activations