© 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. 7-RES-JB
    11. 23369
    Prev
    Next
    INDEX
    Explanations

    words indicating visibility or clarity

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating visibility or clarity of certain situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uden
    -0.79
    nan
    -0.65
    bey
    -0.64
    pping
    -0.63
    ggies
    -0.62
    miah
    -0.62
     tightly
    -0.61
    uese
    -0.61
    akin
    -0.61
    berman
    -0.60
    POSITIVE LOGITS
    iary
    1.24
    aneously
    0.89
     contradictions
    0.88
    ibility
    0.88
    ible
    0.86
     Signs
    0.78
     discrepancies
    0.75
    ibly
    0.74
    iator
    0.74
    URE
    0.74
    Activations Density 0.032%

    No Known Activations