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

    Neuronpedia

    APICircuit 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. 23339
    Prev
    Next
    INDEX
    Explanations

    terms related to physical handling or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "handle" indicating management or control over various situations

    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
    urt
    -0.71
    elong
    -0.69
    esis
    -0.67
    ischer
    -0.66
    egal
    -0.66
    ester
    -0.66
     Thou
    -0.66
    hemat
    -0.65
     recomm
    -0.65
    esters
    -0.64
    POSITIVE LOGITS
    bars
    1.36
     handles
    0.91
     handle
    0.91
     Handle
    0.82
    ttes
    0.75
     grips
    0.73
    bar
    0.72
    handle
    0.69
    lain
    0.68
    Cmd
    0.67
    Activations Density 0.011%

    No Known Activations