© 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. 11-RES-JB
    11. 1405
    Prev
    Next
    INDEX
    Explanations

    names of persons or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criticism and commentary on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?".
    -1.13
    ?ãĢį
    -0.84
    )",
    -0.84
     doesnt
    -0.80
    ?!"
    -0.78
    )).
    -0.76
    \"
    -0.75
    [/
    -0.75
    "))
    -0.75
    )\
    -0.74
    POSITIVE LOGITS
    :
    1.26
    ;
    1.06
    —"
    1.02
    .):
    0.99
     —
    0.99
    —
    0.97
    .:
    0.92
     --
    0.91
    ,—
    0.85
    !:
    0.82
    Activations Density 2.057%

    No Known Activations