© 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. 17926
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, particularly those related to sports teams and cities

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.80
    etheless
    -0.67
    urtles
    -0.61
    reys
    -0.61
    blers
    -0.59
    ylum
    -0.58
    keeping
    -0.57
     leap
    -0.57
    lde
    -0.56
     TAMADRA
    -0.56
    POSITIVE LOGITS
    ateral
    0.80
    azy
    0.74
    AMY
    0.73
    oyd
    0.72
    aptop
    0.72
    cious
    0.70
     Bean
    0.68
     Ron
    0.64
    ansk
    0.64
    utz
    0.64
    Activations Density 0.025%

    No Known Activations