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. 21253
    Prev
    Next
    INDEX
    Explanations

    terms related to frustration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ust."

    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 - anger

    No Comments

    Negative Logits
    perty
    -0.72
    plin
    -0.66
    jack
    -0.63
    ck
    -0.60
    ught
    -0.59
    senal
    -0.59
    lde
    -0.59
    pper
    -0.59
    ket
    -0.58
     Own
    -0.58
    POSITIVE LOGITS
    rations
    1.27
    rator
    1.20
    rious
    1.15
    rans
    1.13
    rated
    1.12
    rating
    1.10
    roph
    1.08
    rine
    1.07
    rates
    1.06
    ribut
    1.04
    Activations Density 0.047%

    No Known Activations