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

    Neuronpedia

    APICircuit 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. 13330
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and activism

    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
    603
    +0.09
    0.6%
    119
    +0.08
    0.6%
    738
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.23
    603
    +0.08
    0.11
    48
    +0.07
    0.10
    Negative Logits
    pite
    -0.60
    idency
    -0.55
    phrine
    -0.55
    bourg
    -0.53
    ateral
    -0.51
    Ocean
    -0.46
    iership
    -0.45
     wound
    -0.45
    nil
    -0.44
     Fault
    -0.44
    POSITIVE LOGITS
    gey
    0.80
    Boo
    0.73
    hest
    0.63
     Boo
    0.63
     boo
    0.63
    ĭ
    0.60
    leans
    0.59
    edIn
    0.56
    esis
    0.56
    gee
    0.56
    Activations Density 7.456%

    No Known Activations