© 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. 36117
    Prev
    Next
    INDEX
    Explanations

    references to decay or deterioration in natural environments

    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
    651
    +0.10
    0.5%
    741
    +0.10
    0.5%
    336
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.10
    0.05
    125
    +0.10
    0.07
    595
    +0.09
    0.05
    Negative Logits
    ´
    -0.76
    º
    -0.68
    £
    -0.64
    ¥ŀ
    -0.64
     [|
    -0.61
    ATHER
    -0.61
    ¥
    -0.61
    ¶ħ
    -0.61
    į
    -0.61
    Ļ½
    -0.60
    POSITIVE LOGITS
    rogen
    0.82
    document
    0.81
    anium
    0.80
    chen
    0.78
    amins
    0.78
    chers
    0.71
    hered
    0.71
    chell
    0.70
    chens
    0.70
    ney
    0.69
    Activations Density 6.870%

    No Known Activations