© 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. 1-RES-JB
    11. 20234
    Prev
    Next
    INDEX
    Explanations

    references to the politician Al Gore

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Al Gore

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akedown
    -0.76
    olog
    -0.69
    ivity
    -0.68
    Constructed
    -0.67
    uously
    -0.64
    riage
    -0.63
    ablished
    -0.61
    uating
    -0.61
    uing
    -0.61
    imen
    -0.59
    POSITIVE LOGITS
    byss
    1.20
     Gore
    1.09
    pedia
    0.86
    vine
    0.78
    bite
    0.76
    achev
    0.76
    hound
    0.75
    boro
    0.74
    bage
    0.74
     contrace
    0.72
    Activations Density 0.003%

    No Known Activations