© 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. 8-RES-JB
    11. 3117
    Prev
    Next
    INDEX
    Explanations

    locations or venues

    oai_token-act-pair · gpt-3.5-turbo

    references to various locations and venues

    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
    onomy
    -0.79
    adapt
    -0.75
    Lear
    -0.71
    omorph
    -0.69
    apter
    -0.68
    outed
    -0.68
    itive
    -0.68
    м
    -0.67
    onom
    -0.65
    itic
    -0.65
    POSITIVE LOGITS
     Stadium
    1.07
     Plaza
    0.98
     Hotel
    0.92
     plaza
    0.89
     Hilton
    0.88
     stadium
    0.87
     entrances
    0.87
     Arena
    0.85
     Coliseum
    0.84
     overlooking
    0.84
    Activations Density 0.229%

    No Known Activations