© 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. 7-RES-JB
    11. 23692
    Prev
    Next
    INDEX
    Explanations

    requests for feedback or comments in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases urging the reader to leave comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alist
    -0.84
    reme
    -0.73
    andan
    -0.72
    kered
    -0.71
    lied
    -0.67
    gio
    -0.67
     Cosponsors
    -0.66
    reader
    -0.65
    ethical
    -0.64
    essee
    -0.63
    POSITIVE LOGITS
     undone
    0.95
    overs
    0.85
     unfinished
    0.76
     aside
    0.75
     behind
    0.72
    ipp
    0.71
     footprints
    0.70
    wich
    0.70
     Behind
    0.69
     untreated
    0.68
    Activations Density 0.040%

    No Known Activations