© 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. 17335
    Prev
    Next
    INDEX
    Explanations

    proper nouns likely related to locations or people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly focusing on their frequent mentions in the text

    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
    acular
    -0.78
     rall
    -0.70
    ition
    -0.68
    pmwiki
    -0.65
    orative
    -0.63
    llular
    -0.63
    uality
    -0.62
     downhill
    -0.61
    âĶĢâĶĢ
    -0.61
    ISION
    -0.61
    POSITIVE LOGITS
    idays
    0.81
    aida
    0.78
    wig
    0.76
    riks
    0.75
    mann
    0.74
    sworth
    0.74
    mong
    0.73
    aday
    0.71
    felt
    0.70
    ancock
    0.70
    Activations Density 0.157%

    No Known Activations