© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    dialogue attributions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly colons and question marks, indicating a focus on dialogue or conversational structures

    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
    etheless
    -0.93
     satell
    -0.88
     antidepress
    -0.81
     exting
    -0.76
    avorite
    -0.76
    escription
    -0.76
     enthusi
    -0.74
    jriwal
    -0.74
     volunte
    -0.73
     encount
    -0.73
    POSITIVE LOGITS
     Huh
    1.43
     Yeah
    1.41
     Oh
    1.37
     Fuck
    1.36
     Okay
    1.32
     Nope
    1.31
     Uh
    1.29
     Hmm
    1.29
     Damn
    1.28
     Shit
    1.27
    Activations Density 0.281%

    No Known Activations