Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23348
    Prev
    Next
    INDEX
    Explanations

    actions indicating physical force or conflict

    oai_token-act-pair · gpt-3.5-turbo

    actions related to restraint or limitation

    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
    Downloadha
    -0.76
     Dragonbound
    -0.74
     Deity
    -0.63
     Raider
    -0.62
     Sorceress
    -0.59
     Ideal
    -0.56
     objected
    -0.56
     Sloven
    -0.56
     Bruins
    -0.55
     Werner
    -0.55
    POSITIVE LOGITS
    ouncing
    1.37
    ping
    1.36
    icating
    1.31
    imating
    1.30
    ulating
    1.29
    reating
    1.29
    iting
    1.28
    iating
    1.25
    asuring
    1.23
    itting
    1.22
    Activations Density 0.269%

    No Known Activations