© 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. 7764
    Prev
    Next
    INDEX
    Explanations

    mentions of medical terms or conditions, particularly those related to research and analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "mediocrity."

    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
     Typh
    -0.65
     redes
    -0.64
    soever
    -0.63
     deeds
    -0.63
    laus
    -0.62
     Canterbury
    -0.62
    ragon
    -0.62
    owship
    -0.61
     Kingdoms
    -0.61
     alternate
    -0.59
    POSITIVE LOGITS
    plom
    1.09
    ples
    1.07
    aceous
    0.97
    orno
    0.96
    pler
    0.92
    ennes
    0.91
    endo
    0.91
    pling
    0.89
    veland
    0.89
    uli
    0.89
    Activations Density 0.059%

    No Known Activations