© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    names and institutions with a pattern of uppercase letter followed by an occasional number

    oai_token-act-pair · gpt-3.5-turbo

    identifiers and names related to commercial and media contexts

    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
     ....
    -0.70
    ..
    -0.63
     [&
    -0.63
    Âł
    -0.63
     ..."
    -0.61
    ....
    -0.61
    âĢķ
    -0.59
     âĢ¦
    -0.58
     ...
    -0.58
    âĢ¦.
    -0.58
    POSITIVE LOGITS
    theless
    0.99
     contends
    0.92
     acknowledges
    0.89
     agrees
    0.88
     believes
    0.88
     concedes
    0.87
     insists
    0.87
     alleges
    0.86
     maintains
    0.86
     concludes
    0.84
    Activations Density 0.473%

    No Known Activations