© 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. 18578
    Prev
    Next
    INDEX
    Explanations

    proper names, possibly related to sports or media figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Troy."

    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
    osures
    -0.77
    pmwiki
    -0.76
    backer
    -0.76
    unknown
    -0.75
    osing
    -0.71
    atform
    -0.69
    asion
    -0.69
    ipper
    -0.68
    ña
    -0.68
    INESS
    -0.66
    POSITIVE LOGITS
    sum
    0.75
    master
    0.74
    edIn
    0.73
    ©¶æ¥µ
    0.71
     Tul
    0.70
    nant
    0.69
     Parish
    0.69
    anus
    0.69
    ij士
    0.69
    er
    0.67
    Activations Density 0.039%

    No Known Activations