© 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. 32871
    Prev
    Next
    INDEX
    Explanations

    information related to business and services

    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
    447
    +0.27
    1.3%
    71
    +0.09
    0.4%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.27
    0.11
    49
    +0.09
    0.14
    142
    +0.09
    0.13
    Negative Logits
    lie
    -0.69
    ollar
    -0.65
    essing
    -0.61
    1111
    -0.58
    osaurus
    -0.57
    lin
    -0.56
    osi
    -0.55
     Neander
    -0.54
    necess
    -0.54
    jac
    -0.54
    POSITIVE LOGITS
    prototype
    0.72
    ONSORED
    0.64
     disbanded
    0.63
    £ı
    0.62
    tesy
    0.62
     founder
    0.59
    ADRA
    0.59
     ITS
    0.59
    ceiver
    0.58
     trending
    0.58
    Activations Density 17.086%

    No Known Activations