© 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. 9-RES-JB
    11. 16152
    Prev
    Next
    INDEX
    Explanations

    locations or directions mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places where actions or events occur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Every Saturdays, Rabbi Goldstein goes to the

    No Comments

    Negative Logits
    ZA
    -0.71
     compared
    -0.67
    Frames
    -0.67
    rel
    -0.67
     =================
    -0.67
    quel
    -0.65
    ;}
    -0.64
    rored
    -0.64
    contained
    -0.64
    Analysis
    -0.63
    POSITIVE LOGITS
     Scotia
    0.73
     Starbucks
    0.71
     Fargo
    0.71
     Osh
    0.70
     Bethesda
    0.69
     downtown
    0.69
     Beaver
    0.69
     Café
    0.68
     Chinatown
    0.68
     booth
    0.67
    Activations Density 0.245%

    No Known Activations