© 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 Local
    9. 6-RES_SCL-AJT
    11. 35472
    Prev
    Next
    INDEX
    Explanations

    Spanish words relating to politics and governance

    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
    218
    +0.13
    0.5%
    103
    +0.12
    0.5%
    533
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.13
    103
    +0.12
    0.14
    556
    +0.11
    0.12
    Negative Logits
    PR
    -0.89
    MP
    -0.82
    SR
    -0.82
    GP
    -0.80
     Seg
    -0.77
    UP
    -0.77
    CP
    -0.77
    CR
    -0.77
    SM
    -0.76
    POST
    -0.75
    POSITIVE LOGITS
    obile
    0.93
    ortal
    0.88
    å
    0.86
    ionage
    0.85
    ģĸ
    0.82
    orescence
    0.81
    asonic
    0.80
    andise
    0.79
    utic
    0.79
    Ó
    0.79
    Activations Density 5.711%

    No Known Activations