© 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. 6-RES-JB
    11. 2677
    Prev
    Next
    INDEX
    Explanations

    states and territories mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific states or geopolitical entities

    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
    bor
    -0.78
    othy
    -0.69
    hod
    -0.68
    rious
    -0.68
     Grave
    -0.67
    erb
    -0.64
    rang
    -0.62
    raid
    -0.62
    edi
    -0.61
    imens
    -0.60
    POSITIVE LOGITS
     apiece
    1.00
     nationwide
    0.88
     vying
    0.84
     worldwide
    0.82
     including
    0.78
    inois
    0.74
     surveyed
    0.74
     nomine
    0.74
     totaling
    0.73
     statewide
    0.72
    Activations Density 0.159%

    No Known Activations