© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10798
    Prev
    Next
    INDEX
    Explanations

    keywords related to amphibians

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with amphibians and related biological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cigars
    -0.80
    fare
    -0.69
    naire
    -0.69
     beard
    -0.68
     stink
    -0.67
     Fargo
    -0.65
     smoking
    -0.64
     shroud
    -0.64
    knife
    -0.64
    advertising
    -0.63
    POSITIVE LOGITS
    oint
    0.88
    ilater
    0.83
     Amph
    0.82
    ious
    0.78
    merce
    0.78
    issan
    0.77
    ienced
    0.76
    iences
    0.76
    ity
    0.76
    alan
    0.74
    Activations Density 0.023%

    No Known Activations