© 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. 18703
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Ajmer."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to specific places or names

    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
    LESS
    -0.68
     Lobby
    -0.64
    Balt
    -0.63
    ALLY
    -0.63
    bucks
    -0.62
    Catal
    -0.62
     Mobil
    -0.60
     Yards
    -0.59
     ABV
    -0.58
     Lesbian
    -0.58
    POSITIVE LOGITS
    awar
    0.93
    unction
    0.91
    argon
    0.86
    ourning
    0.83
    lege
    0.82
    asma
    0.82
    ournal
    0.82
    cale
    0.81
    ecause
    0.81
    ascript
    0.80
    Activations Density 0.077%

    No Known Activations