© 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. 1-RES-JB
    11. 9410
    Prev
    Next
    INDEX
    Explanations

    descriptive terms referring to a brief moment or representation of data

    oai_token-act-pair · gpt-3.5-turbo

    references to snapshots or representations of data or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iant
    -0.84
    doms
    -0.84
    anooga
    -0.80
    anguage
    -0.80
    eri
    -0.79
    ugu
    -0.77
    ongs
    -0.77
    adh
    -0.74
    onge
    -0.74
    ressive
    -0.74
    POSITIVE LOGITS
     snapshots
    1.07
     snapshot
    1.06
     VERS
    0.83
     TABLE
    0.77
     "$:/
    0.75
     photograph
    0.74
    inventoryQuantity
    0.73
     Blueprint
    0.69
     Lans
    0.69
     tranquil
    0.68
    Activations Density 0.032%

    No Known Activations