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. 34314
    Prev
    Next
    INDEX
    Explanations

    phrases related to magic and spells

    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
    +0.23
    1.0%
    288
    +0.22
    0.9%
    642
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.23
    0.19
    589
    +0.22
    0.06
    351
    +0.15
    0.03
    Negative Logits
    Filename
    -0.86
    bis
    -0.82
     Fas
    -0.82
    fam
    -0.81
    hovah
    -0.79
    arers
    -0.79
    alis
    -0.78
    eming
    -0.77
    ribute
    -0.77
    uran
    -0.76
    POSITIVE LOGITS
     tricks
    0.97
     wand
    0.91
     Leap
    0.91
    ãĥĥãĤ¯
    0.88
     realism
    0.88
    binding
    0.86
     mushrooms
    0.85
     carpet
    0.81
     lantern
    0.81
    istry
    0.79
    Activations Density 7.988%

    No Known Activations