© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40826
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets

    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
    127
    +0.07
    0.5%
    534
    +0.07
    0.4%
    494
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.07
    0.23
    49
    +0.07
    0.10
    534
    +0.06
    0.04
    Negative Logits
    bourg
    -0.47
    lehem
    -0.46
    krit
    -0.44
     simultane
    -0.43
    lov
    -0.43
    soever
    -0.43
     Hass
    -0.42
    atin
    -0.42
     tort
    -0.42
    ategory
    -0.42
    POSITIVE LOGITS
    xd
    0.55
    xe
    0.54
    x
    0.54
    xa
    0.51
    uer
    0.47
    xff
    0.46
     downtime
    0.46
    APD
    0.45
    446
    0.44
    ]=
    0.44
    Activations Density 9.663%

    No Known Activations