© 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. 10-RES-JB
    11. 10174
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of specific places and entities

    oai_token-act-pair · gpt-3.5-turbo

    negative or contradictory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -0.70
    "—
    -0.53
    ],"
    -0.49
    umbn
    -0.48
    —"
    -0.45
    )—
    -0.45
     Olympic
    -0.45
    igenous
    -0.44
    farious
    -0.42
    blown
    -0.42
    POSITIVE LOGITS
     tho
    0.64
     didnt
    0.59
     dont
    0.58
     pics
    0.58
     alot
    0.57
     doesnt
    0.53
     google
    0.52
     ital
    0.51
     reprint
    0.48
    ittens
    0.48
    Activations Density 0.849%

    No Known Activations