© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations, such as cities and states

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and significant entities, particularly locations and titles

    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
    371
    -0.74
    352
    -0.73
     ip
    -0.73
    036
    -0.73
     Mai
    -0.72
     Ib
    -0.72
    axter
    -0.71
     Bos
    -0.70
     iP
    -0.70
     nas
    -0.69
    POSITIVE LOGITS
    st
    1.16
    sts
    1.16
    stan
    1.10
    ster
    1.10
    ST
    1.08
     Street
    1.07
     Starr
    1.03
    STER
    1.03
    stice
    0.96
    este
    0.96
    Activations Density 0.248%

    No Known Activations