© 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. 10-RES-JB
    11. 12854
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographical locations, specifically the Sambisa Forest

    oai_token-act-pair · gpt-3.5-turbo

    the presence of certain letters or prominent characters in names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scarborough
    -0.60
     starters
    -0.56
     bec
    -0.55
    stood
    -0.55
     gon
    -0.54
     merc
    -0.54
     Progressive
    -0.54
    BILITY
    -0.53
     trump
    -0.53
     coli
    -0.53
    POSITIVE LOGITS
    urat
    1.02
    ali
    1.00
    akin
    0.96
    iru
    0.96
    oola
    0.95
    orie
    0.94
    aja
    0.93
    iri
    0.92
    ari
    0.91
    ila
    0.91
    Activations Density 0.107%

    No Known Activations