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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 15035
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words that indicate relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.81
    ESA
    -0.65
    HM
    -0.64
    ruary
    -0.63
    ascript
    -0.60
    externalActionCode
    -0.60
    ĸļ
    -0.59
     nomine
    -0.58
    lication
    -0.58
    ESE
    -0.58
    POSITIVE LOGITS
     chops
    0.60
    owl
    0.56
     feat
    0.55
    fork
    0.54
    ĪĴ
    0.54
    Bone
    0.54
     flakes
    0.54
    sect
    0.54
     wheels
    0.53
    Ingredients
    0.53
    Activations Density 0.464%

    No Known Activations