© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3219
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their relationships, especially in the context of work or partnerships

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their background or relationships

    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
     issu
    -0.65
    amacare
    -0.63
     uncertainties
    -0.63
    verage
    -0.63
     Transparency
    -0.62
     polarized
    -0.62
    itivity
    -0.62
    raq
    -0.62
     reiterate
    -0.62
    osphere
    -0.61
    POSITIVE LOGITS
    çĶ°
    0.88
     fame
    0.81
    brother
    0.72
    catentry
    0.72
     nephew
    0.70
     Fell
    0.69
     Earl
    0.69
     pian
    0.68
    76561
    0.68
     pseudonym
    0.67
    Activations Density 1.027%

    No Known Activations