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. 11-RES-JB
    6. 8790
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions involving contact or movement

    oai_token-act-pair · gpt-3.5-turbo

    words associated with sounds and actions made by characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    channelAvailability
    -0.78
    quickShipAvailable
    -0.73
     insider
    -0.73
     successors
    -0.69
     insiders
    -0.68
     representative
    -0.67
     favorable
    -0.67
     establishment
    -0.66
     correct
    -0.66
     merit
    -0.66
    POSITIVE LOGITS
    rawled
    1.27
    atted
    1.21
    ogged
    1.20
    armed
    1.17
    attered
    1.16
    uffed
    1.15
    umbled
    1.14
    umbling
    1.14
    rolled
    1.13
    ucked
    1.12
    Activations Density 0.124%

    No Known Activations