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. 14276
    Prev
    Next
    INDEX
    Explanations

    the last name "Soderbergh"

    oai_token-act-pair · gpt-3.5-turbo

    words related to individuals with specific roles in the film industry

    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
     Gazette
    -0.74
     Acts
    -0.67
     Lovecraft
    -0.64
     Sri
    -0.61
    idences
    -0.61
     Indiana
    -0.61
     Bethlehem
    -0.59
     Samoa
    -0.59
     Fact
    -0.56
    ees
    -0.56
    POSITIVE LOGITS
    oder
    1.24
    aton
    0.97
    ception
    0.92
    rors
    0.89
    ode
    0.84
    ror
    0.84
    sonian
    0.83
    velop
    0.83
    lang
    0.82
    meier
    0.81
    Activations Density 0.007%

    No Known Activations