© 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. 9-RES-JB
    11. 14226
    Prev
    Next
    INDEX
    Explanations

    instances in the text where the word "leave" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging the reader to leave comments or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alist
    -0.82
     Cosponsors
    -0.81
    andan
    -0.74
    lied
    -0.70
    ieval
    -0.69
    kered
    -0.66
    gio
    -0.65
    issance
    -0.65
    ians
    -0.61
    tie
    -0.61
    POSITIVE LOGITS
     aside
    1.10
     undone
    1.09
     unfinished
    0.87
    overs
    0.86
     behind
    0.85
     footprints
    0.84
     unanswered
    0.81
     untouched
    0.81
     voic
    0.81
     Behind
    0.79
    Activations Density 0.046%

    No Known Activations