© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    references to a specific city

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific city or municipalities involved in various contexts

    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
    zees
    -1.00
    iameter
    -0.88
     Lanka
    -0.77
     Countries
    -0.77
    chio
    -0.76
    terday
    -0.75
    ãĥ¼ãĥĨ
    -0.73
    pmwiki
    -0.72
     Brilliant
    -0.71
    etsk
    -0.70
    POSITIVE LOGITS
    wide
    1.22
     council
    1.13
     attorney
    1.05
     councillor
    1.00
     skyline
    0.98
     mayor
    0.97
     solicitor
    0.96
     ordinance
    0.93
     clerk
    0.93
    scape
    0.91
    Activations Density 0.050%

    No Known Activations