© 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. 9-RES-JB
    11. 7268
    Prev
    Next
    INDEX
    Explanations

    phrases related to geology and earth sciences

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and terms related to societal issues and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshop
    -0.78
    hift
    -0.73
    ĸļ
    -0.70
    htaking
    -0.62
    ickr
    -0.61
    CAP
    -0.61
     Investigation
    -0.59
    canon
    -0.58
    EStream
    -0.58
    ynthesis
    -0.58
    POSITIVE LOGITS
     bodies
    1.10
     objects
    1.00
     entities
    1.00
     occupants
    0.98
     organisms
    0.96
     units
    0.95
     components
    0.94
     populations
    0.92
     creatures
    0.91
     beings
    0.91
    Activations Density 0.791%

    No Known Activations