© 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. 1810
    Prev
    Next
    INDEX
    Explanations

    responses or reactions to statements or questions

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue and responses in the text

    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
    arta
    -0.66
    erella
    -0.62
    ICES
    -0.60
     Syndicate
    -0.59
    illon
    -0.59
    illac
    -0.58
    ewater
    -0.58
     ILCS
    -0.56
    oris
    -0.55
    Pont
    -0.54
    POSITIVE LOGITS
     affirm
    1.22
     angrily
    1.04
     sarcast
    1.02
     positively
    0.92
     emphatically
    0.92
     favorably
    0.90
     negatively
    0.90
     enthusiastically
    0.90
     bluntly
    0.88
     saying
    0.88
    Activations Density 0.055%

    No Known Activations