© 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. 1364
    Prev
    Next
    INDEX
    Explanations

    opinions or speculative statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinions or assertions

    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
    Notable
    -0.71
    sing
    -0.67
    ership
    -0.65
    Merit
    -0.64
    comed
    -0.64
    cele
    -0.63
    Frames
    -0.63
     Afterwards
    -0.62
    ]).
    -0.61
    knit
    -0.61
    POSITIVE LOGITS
     answer
    1.56
    Answer
    1.46
     Answer
    1.42
     answers
    1.29
    swers
    1.23
     answered
    1.09
     answ
    0.97
    answer
    0.95
     reply
    0.94
     answering
    0.89
    Activations Density 0.532%

    No Known Activations