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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16662
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific products or actions

    oai_token-act-pair · gpt-3.5-turbo

    nouns that are related to various subjects, including gaming, food, and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAPTER
    -0.68
    Higher
    -0.68
    ormonal
    -0.65
    abyte
    -0.63
    igious
    -0.63
    FINE
    -0.61
    ordinate
    -0.60
    luster
    -0.59
    chy
    -0.59
    asonable
    -0.59
    POSITIVE LOGITS
     Cyn
    0.69
    iasco
    0.69
    plates
    0.68
    ographs
    0.65
    utra
    0.63
    ombat
    0.63
     Chronicles
    0.60
     suprem
    0.58
    fecture
    0.58
    ighters
    0.58
    Activations Density 0.527%

    No Known Activations