© 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. 9944
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Chrom" (possibly referring to "Chrome" or "Chromium")

    oai_token-act-pair · gpt-3.5-turbo

    references to the Chromecast device and cheese-related terms

    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
     LCS
    -0.67
    CVE
    -0.64
     attribution
    -0.64
    ACP
    -0.57
     Nile
    -0.57
     issuer
    -0.57
     CARD
    -0.57
     retrospective
    -0.56
     refere
    -0.55
     corrections
    -0.54
    POSITIVE LOGITS
    ecake
    1.33
    ecast
    1.25
    ophon
    1.22
    ebook
    1.22
    ium
    1.15
    eb
    1.15
    ec
    1.09
    ophone
    1.06
    olith
    1.04
    ophobic
    1.03
    Activations Density 0.063%

    No Known Activations