© 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. 2332
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to causing harm or distress to oneself or others

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional or physical impact on individuals

    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
    uve
    -0.65
    ooters
    -0.63
     Pastebin
    -0.60
    Initialized
    -0.53
    sett
    -0.49
    ipop
    -0.47
     advertised
    -0.47
    aber
    -0.46
     Inher
    -0.45
    Haunted
    -0.45
    POSITIVE LOGITS
     to
    0.98
    to
    0.92
    To
    0.73
     TO
    0.72
     undue
    0.71
     tremendous
    0.69
     immense
    0.69
     considerable
    0.68
    TO
    0.67
    into
    0.65
    Activations Density 0.239%

    No Known Activations