© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17328
    Prev
    Next
    INDEX
    Explanations

    names with the initial "K" followed by a rating number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "K" in names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.63
     tense
    -0.62
     Collider
    -0.61
     Polly
    -0.61
     Soldiers
    -0.55
     AAA
    -0.55
     rainy
    -0.55
     billboards
    -0.54
     CPR
    -0.54
     polio
    -0.53
    POSITIVE LOGITS
    aminer
    1.28
    rieg
    1.22
    essel
    1.13
    avan
    1.11
    oval
    1.10
    arel
    1.03
    arp
    1.03
    aspers
    1.02
    oop
    1.01
    udos
    1.01
    Activations Density 0.033%

    No Known Activations