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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 21344
    Prev
    Next
    INDEX
    Explanations

    subjects related to handedness, specifically identifying "left-handed" mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to handedness, particularly "left-handed" and "right-handed" distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anamo
    -0.98
    burgh
    -0.82
    CHAT
    -0.82
    raltar
    -0.79
    idian
    -0.77
    oother
    -0.77
    ĸļ
    -0.76
    ublic
    -0.76
    qqa
    -0.76
    liam
    -0.75
    POSITIVE LOGITS
     nodd
    1.02
    ness
    0.95
     clutch
    0.86
    handed
    0.76
     clut
    0.76
     luggage
    0.74
     dexterity
    0.71
    nesses
    0.71
     barb
    0.70
     thumb
    0.69
    Activations Density 0.022%

    No Known Activations