© 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. 2-RES-JB
    11. 12473
    Prev
    Next
    INDEX
    Explanations

    words related to movement and exploring freely in different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "roaming" and its variants, in addition to some specific mentions of "roommate" and "feral."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.82
    emis
    -0.73
    ifice
    -0.69
    ilts
    -0.69
    ribute
    -0.67
    gur
    -0.66
    uras
    -0.66
    emi
    -0.64
    stood
    -0.64
    sharp
    -0.64
    POSITIVE LOGITS
     roaming
    1.23
     roam
    1.12
    Roaming
    0.85
     packs
    0.74
    lust
    0.70
     averages
    0.70
     charges
    0.69
    esses
    0.66
     creeps
    0.66
     pack
    0.65
    Activations Density 0.014%

    No Known Activations