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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 8538
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consequences or costs associated with certain actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating significant costs or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    halla
    -0.78
    atis
    -0.72
    execute
    -0.68
    uploads
    -0.68
    docs
    -0.63
    USA
    -0.62
    eki
    -0.59
    hex
    -0.58
     Fame
    -0.58
    produ
    -0.57
    POSITIVE LOGITS
     inconvenient
    0.82
     expense
    0.79
    quickShipAvailable
    0.79
     cost
    0.73
     intersections
    0.73
     heels
    0.73
    onement
    0.72
     twilight
    0.69
     costing
    0.69
     risk
    0.65
    Activations Density 0.129%

    No Known Activations