© 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. 3705
    Prev
    Next
    INDEX
    Explanations

    word pairs or short phrases that may be negative or critical in tone

    oai_token-act-pair · gpt-3.5-turbo

    derogatory or insulting language towards individuals or groups

    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
    estyle
    -0.74
    encer
    -0.72
    aez
    -0.71
    rowth
    -0.69
     emphasizes
    -0.69
    toggle
    -0.69
    encers
    -0.68
    imity
    -0.68
    styles
    -0.68
    arsity
    -0.67
    POSITIVE LOGITS
     pathetic
    1.47
     hideous
    1.41
     wretched
    1.37
     ludicrous
    1.34
     laughable
    1.31
     appalling
    1.30
     ridiculous
    1.30
     disgusting
    1.29
     utterly
    1.28
     despicable
    1.28
    Activations Density 1.032%

    No Known Activations