Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45272
    Prev
    Next
    INDEX
    Explanations

    text related to a specific fungus, specifically the genus Scutellinia

    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
    679
    +0.20
    0.7%
    284
    +0.17
    0.6%
    238
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.20
    0.08
    165
    +0.17
    0.04
    203
    +0.16
    0.07
    Negative Logits
     compr
    -0.95
    #$
    -0.89
     challeng
    -0.84
    isSpecialOrderable
    -0.82
    wcs
    -0.81
    issance
    -0.81
    nect
    -0.81
    cale
    -0.79
     resil
    -0.79
     contrasting
    -0.79
    POSITIVE LOGITS
    ierrez
    1.83
    opian
    1.54
    rition
    1.53
    iful
    1.50
    tle
    1.46
    rient
    1.44
    ifully
    1.43
    anamo
    1.43
    opia
    1.40
    ilitarian
    1.36
    Activations Density 5.115%

    No Known Activations