© 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. 10134
    Prev
    Next
    INDEX
    Explanations

    phrases related to misunderstandings or disagreements in social interactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confusion or frustration about a situation

    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
     ÂŃ
    -1.11
    âĢij
    -1.06
    —
    -0.98
    Footnote
    -0.87
    ®,
    -0.79
    Thirty
    -0.76
    Enlarge
    -0.76
    –
    -0.75
    "—
    -0.73
    )—
    -0.72
    POSITIVE LOGITS
     didnt
    1.71
     doesnt
    1.69
     dont
    1.68
     alot
    1.47
     lol
    1.35
     english
    1.35
     tho
    1.34
    nt
    1.29
     dmg
    1.17
     wont
    1.17
    Activations Density 1.078%

    No Known Activations