© 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. 12736
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles and academic affiliations, particularly in the field of academia

    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
    556
    +0.14
    0.6%
    659
    +0.14
    0.5%
    118
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.14
    0.13
    701
    +0.14
    0.07
    659
    +0.12
    0.09
    Negative Logits
     Fenrir
    -0.83
    SOURCE
    -0.80
    Ïī
    -0.75
    illusion
    -0.74
    scl
    -0.73
     Advocate
    -0.73
     thor
    -0.70
    Scope
    -0.70
    Bell
    -0.69
    need
    -0.69
    POSITIVE LOGITS
    pta
    0.96
    enza
    0.94
    iaz
    0.92
    ibo
    0.91
    ciating
    0.90
    cific
    0.90
    nikov
    0.84
    ione
    0.83
    encia
    0.82
    abad
    0.81
    Activations Density 11.770%

    No Known Activations