© 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. 22333
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences or statements, potentially related to economic or social issues

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence structure cues

    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
    tesy
    -0.86
    itely
    -0.81
    itled
    -0.74
    itional
    -0.74
    igent
    -0.72
    itionally
    -0.70
    bara
    -0.68
    uers
    -0.67
    ovember
    -0.66
    anni
    -0.66
    POSITIVE LOGITS
     Anything
    1.20
     Whatever
    1.19
    etc
    1.15
     Everywhere
    1.09
     Worse
    1.07
     And
    1.05
     Nope
    1.03
     Anyway
    1.03
     Unsure
    1.02
     Repeat
    1.00
    Activations Density 0.272%

    No Known Activations