© 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. 11-RES-JB
    11. 17146
    Prev
    Next
    INDEX
    Explanations

    references to achievements or recognitions like inductions into halls of fame

    oai_token-act-pair · gpt-3.5-turbo

    terms related to induction and significant transitions or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rek
    -0.61
     Few
    -0.55
    anges
    -0.54
    weather
    -0.54
    rish
    -0.53
     Rally
    -0.52
     Stability
    -0.52
     rall
    -0.52
     attRot
    -0.51
    otics
    -0.50
    POSITIVE LOGITS
     into
    2.27
     INTO
    1.93
     Into
    1.88
    into
    1.84
     onto
    1.55
    interstitial
    0.92
     overboard
    0.78
    iday
    0.78
     toward
    0.76
     towards
    0.75
    Activations Density 0.363%

    No Known Activations