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. 1-RES-JB
    6. 23634
    Prev
    Next
    INDEX
    Explanations

    concepts related to instincts and reactions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to instinct and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.60
    ĵĺ
    -0.39
    ccording
    -0.39
    Interstitial
    -0.38
    merce
    -0.36
    arel
    -0.36
    cel
    -0.35
     WATCHED
    -0.34
     nanop
    -0.34
    cling
    -0.34
    POSITIVE LOGITS
    smanship
    0.52
    eers
    0.47
    ierre
    0.45
    wagon
    0.44
    igible
    0.43
    代
    0.42
    edin
    0.41
    illo
    0.41
    buster
    0.40
    ista
    0.40
    Activations Density 2.754%

    No Known Activations