© 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. 7-RES-JB
    11. 1515
    Prev
    Next
    INDEX
    Explanations

    celebrity news and gossip

    oai_token-act-pair · gpt-3.5-turbo

    details about personal experiences in celebrity interviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abwe
    -0.77
    azard
    -0.77
     dilig
    -0.77
     defe
    -0.76
    pdf
    -0.76
     Implementation
    -0.76
     weaken
    -0.76
    PDF
    -0.75
     corrosion
    -0.74
     deterrence
    -0.74
    POSITIVE LOGITS
     Beyon
    1.45
     Playboy
    1.38
     onstage
    1.35
     backstage
    1.29
     actresses
    1.29
     Kanye
    1.27
     MTV
    1.25
     Grammy
    1.23
     Rih
    1.22
     actress
    1.21
    Activations Density 0.932%

    No Known Activations