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. 9-RES-JB
    6. 21532
    Prev
    Next
    INDEX
    Explanations

    references to expressions of surprise or shock, often conveyed through verbal exclamations

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of 'asp' or 'asm' suffix structures, often indicating a focus on diseases or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 9 - surprise

    No Comments

    Negative Logits
    hart
    -0.79
    venge
    -0.68
    house
    -0.62
    der
    -0.62
    ball
    -0.61
     credits
    -0.59
    stay
    -0.59
    DER
    -0.59
    hardt
    -0.58
     premiums
    -0.56
    POSITIVE LOGITS
    hemy
    1.19
    ics
    1.01
    asp
    0.99
    vernment
    0.96
    hemer
    0.93
    inator
    0.93
    hest
    0.90
    osure
    0.87
    utic
    0.87
    bian
    0.87
    Activations Density 0.144%

    No Known Activations