© 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. 11-RES-JB
    11. 7026
    Prev
    Next
    INDEX
    Explanations

    keywords related to analyzing information or data

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to analysis, assessment, and change

    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
     theirs
    -0.93
    Its
    -0.84
     hers
    -0.80
     thereof
    -0.77
    Their
    -0.76
    They
    -0.76
    they
    -0.74
     thats
    -0.72
     Its
    -0.65
    their
    -0.65
    POSITIVE LOGITS
     Flavoring
    0.57
     the
    0.55
    avorite
    0.54
     GHC
    0.49
     various
    0.47
     theoretical
    0.46
     an
    0.46
     Starfleet
    0.45
     Microsoft
    0.44
     several
    0.44
    Activations Density 1.095%

    No Known Activations