© 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. 6-RES-JB
    11. 2826
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Lane, potentially related to sports or other activities involving physicality

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lane."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ority
    -0.81
    ulatory
    -0.80
    ģĸ
    -0.74
    atem
    -0.72
    iterranean
    -0.71
    ional
    -0.71
    krit
    -0.69
     Seym
    -0.68
    raints
    -0.67
    urated
    -0.67
    POSITIVE LOGITS
     Lane
    0.96
    lane
    0.82
    backer
    0.76
    holder
    0.74
    ige
    0.73
    agle
    0.73
    ©¶æ
    0.66
    holders
    0.66
    CTV
    0.65
    brand
    0.63
    Activations Density 0.028%

    No Known Activations