© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    URLs of Twitter profiles

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web addresses associated with Twitter

    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
     deserts
    -0.75
     lung
    -0.74
     rehears
    -0.74
     deposits
    -0.72
     deposit
    -0.71
     cholesterol
    -0.70
     audition
    -0.70
     ovarian
    -0.69
     Archdemon
    -0.69
     reptiles
    -0.68
    POSITIVE LOGITS
    hash
    1.36
    realDonaldTrump
    1.25
    groups
    1.21
    intent
    1.13
    pages
    1.13
    search
    1.12
    events
    1.11
    sports
    1.08
    aic
    1.05
    say
    1.05
    Activations Density 0.023%

    No Known Activations