© 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. 0-RES-JB
    11. 6590
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific physical actions or maneuvers

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific terminology related to tactical or strategic approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onomic
    -0.77
    archives
    -0.65
     Bullets
    -0.64
     informed
    -0.64
     pauses
    -0.64
     duplication
    -0.63
    cube
    -0.62
     juggling
    -0.62
    morph
    -0.62
    papers
    -0.58
    POSITIVE LOGITS
     tack
    3.44
    Beat
    1.38
     scant
    1.14
    worldly
    1.06
    aband
    0.99
    ptive
    0.95
     tact
    0.95
     Brands
    0.93
    Course
    0.90
    etting
    0.83
    Activations Density 0.050%

    No Known Activations