© 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. 9-RES-JB
    11. 10180
    Prev
    Next
    INDEX
    Explanations

    proper nouns or subjects of specific actions

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the verbs "come" and "came."

    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
    pmwiki
    -0.67
    IELD
    -0.66
    nesota
    -0.66
    ording
    -0.65
    paren
    -0.63
    olor
    -0.60
    natureconservancy
    -0.59
     ---------
    -0.57
    Discuss
    -0.57
    nature
    -0.57
    POSITIVE LOGITS
     forth
    1.01
     undone
    0.88
     ashore
    0.82
     roaring
    0.79
     closer
    0.78
    arthed
    0.77
     Forth
    0.75
     out
    0.75
     forward
    0.74
     knocking
    0.74
    Activations Density 0.088%

    No Known Activations