© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6175
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collecting or gathering actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.67
    gap
    -0.65
    rouse
    -0.61
    ate
    -0.60
    robe
    -0.60
    hill
    -0.57
    nom
    -0.57
    aminer
    -0.56
     Peninsula
    -0.55
    roma
    -0.55
    POSITIVE LOGITS
     kinds
    1.29
     sorts
    1.27
    igators
    1.13
    igator
    1.13
    usions
    1.09
    ocating
    1.05
    udes
    0.99
    iances
    0.93
    oys
    0.89
    uding
    0.88
    Activations Density 0.111%

    No Known Activations