© 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. 2-RES-JB
    11. 4423
    Prev
    Next
    INDEX
    Explanations

    qualifiers or judgments expressing approval or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quality and moral qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shire
    -0.78
    worm
    -0.75
    warming
    -0.72
    ELD
    -0.70
    OLD
    -0.68
    berman
    -0.67
    tower
    -0.67
    orman
    -0.66
    ortium
    -0.65
    guard
    -0.65
    POSITIVE LOGITS
    itatively
    1.29
    iological
    0.97
    atically
    0.93
     sidx
    0.88
     qual
    0.85
     externalToEVAOnly
    0.84
    iations
    0.83
     guiActiveUn
    0.81
     Flavoring
    0.79
    iology
    0.78
    Activations Density 0.030%

    No Known Activations