© 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. 11-RES-JB
    11. 713
    Prev
    Next
    INDEX
    Explanations

    terms related to junk items or products

    oai_token-act-pair · gpt-3.5-turbo

    references to "junk" and junk food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BRE
    -0.61
     unintended
    -0.61
     Lauder
    -0.60
     Compliance
    -0.60
     Verge
    -0.60
    oral
    -0.60
     brim
    -0.59
    soType
    -0.58
    Plex
    -0.57
     Advocate
    -0.56
    POSITIVE LOGITS
    alos
    1.12
    ies
    1.12
    ie
    1.07
    irk
    0.98
    etry
    0.90
    buster
    0.89
    ularity
    0.89
    ular
    0.89
    aby
    0.88
    ed
    0.88
    Activations Density 0.075%

    No Known Activations