© 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. 8-RES-JB
    11. 17194
    Prev
    Next
    INDEX
    Explanations

    dialogue lines encapsulated in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pole
    -0.86
     targeted
    -0.78
     characterized
    -0.78
     predomin
    -0.73
     frontline
    -0.73
     undersc
    -0.73
     differentiated
    -0.73
     litter
    -0.72
     innov
    -0.72
     consumer
    -0.70
    POSITIVE LOGITS
    Hmm
    1.58
    Hey
    1.57
    Oh
    1.56
    Huh
    1.54
    Yeah
    1.54
    Fuck
    1.48
    Alright
    1.48
    Okay
    1.47
    Uh
    1.45
    Eh
    1.45
    Activations Density 0.094%

    No Known Activations