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. 3-RES-JB
    6. 807
    Prev
    Next
    INDEX
    Explanations

    the word "aff" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific person or character named "Jeff" or related derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHR
    -0.88
    senal
    -0.66
    OPER
    -0.62
     Sagan
    -0.59
     Scream
    -0.59
    worldly
    -0.59
    GV
    -0.58
     ult
    -0.58
    Cam
    -0.57
     timetable
    -0.56
    POSITIVE LOGITS
    onso
    1.10
    inia
    1.04
    irmation
    1.04
    iliation
    1.03
    idav
    1.03
    ield
    1.02
    irms
    1.00
    iliate
    0.99
    irmed
    0.99
    licted
    0.97
    Activations Density 0.007%

    No Known Activations