© 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. 3186
    Prev
    Next
    INDEX
    Explanations

    requests or expressions of hope for people to enjoy or like something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope or encouragement directed towards the audience

    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
     Canaver
    -0.84
     Slave
    -0.65
     Cao
    -0.65
     Osw
    -0.64
     Hutch
    -0.64
    ELD
    -0.64
    ipal
    -0.63
    apo
    -0.61
    é¾įå¥ij士
    -0.61
     Polk
    -0.60
    POSITIVE LOGITS
     appreciate
    0.90
    tub
    0.89
    're
    0.88
    RS
    0.84
     guys
    0.84
    sylv
    0.83
     enjoy
    0.83
     understand
    0.82
    sten
    0.78
    'll
    0.76
    Activations Density 0.099%

    No Known Activations