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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18634
    Prev
    Next
    INDEX
    Explanations

    terms related to constants and numerical values, potentially in the context of various subjects such as biology or mathematics

    oai_token-act-pair · gpt-3.5-turbo

    references to constants in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.77
    gom
    -0.75
    ologies
    -0.73
    CHAT
    -0.73
    itism
    -0.70
    geist
    -0.68
    Crash
    -0.68
     Forbidden
    -0.68
    TN
    -0.68
    aska
    -0.68
    POSITIVE LOGITS
    uation
    0.81
    weights
    0.80
    uates
    0.79
    iating
    0.79
    weight
    0.78
    uated
    0.77
    cy
    0.77
    urity
    0.77
    uating
    0.76
    isation
    0.75
    Activations Density 0.027%

    No Known Activations