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. 45309
    Prev
    Next
    INDEX
    Explanations

    information regarding news coverage, events, and actions

    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
    592
    +0.13
    0.7%
    477
    +0.10
    0.6%
    248
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.13
    -0.09
    754
    +0.10
    0.11
    266
    +0.08
    0.29
    Negative Logits
    geist
    -0.67
    gow
    -0.65
    semb
    -0.63
     coord
    -0.63
    umably
    -0.58
    erent
    -0.58
    terday
    -0.57
    imilar
    -0.57
    xual
    -0.56
    itialized
    -0.56
    POSITIVE LOGITS
     subscription
    0.79
    Subscribe
    0.72
     subscribing
    0.72
     subscriptions
    0.70
     subscribe
    0.68
    FREE
    0.62
     FREE
    0.62
     premium
    0.61
     email
    0.59
     CLICK
    0.59
    Activations Density 14.189%

    No Known Activations