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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 7996
    Prev
    Next
    INDEX
    Explanations

    terms related to movement or action in a particular location or context, such as roaming, wandering, or stalking

    oai_token-act-pair · gpt-3.5-turbo

    words related to movement or travel, particularly forms of roaming and stalking

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

    No Comments

    Negative Logits
    older
    -0.78
    ilts
    -0.76
    ifice
    -0.76
    emis
    -0.75
    uyomi
    -0.72
    nesium
    -0.71
    cision
    -0.68
    gio
    -0.68
    rogen
    -0.68
    iyah
    -0.66
    POSITIVE LOGITS
     roaming
    0.97
     roam
    0.90
    lust
    0.79
    DON
    0.73
    lyak
    0.71
    lords
    0.69
     charges
    0.68
    Roaming
    0.66
     packs
    0.64
    CLASSIFIED
    0.63
    Activations Density 0.009%

    No Known Activations