© 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. 13503
    Prev
    Next
    INDEX
    Explanations

    the word "thin" and words related to thinness or thin materials

    oai_token-act-pair · gpt-3.5-turbo

    references to thinness or thin materials

    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
    bucks
    -0.70
     Compass
    -0.68
    ILLE
    -0.68
     Pact
    -0.66
    OUP
    -0.66
     Volt
    -0.65
    Particip
    -0.65
    udeau
    -0.64
    ilee
    -0.63
    pheus
    -0.62
    POSITIVE LOGITS
    ned
    1.45
    ning
    1.35
    ners
    1.21
    nesses
    1.07
    nery
    0.89
    ness
    0.87
    ened
    0.86
    odynamic
    0.85
    ner
    0.84
    neck
    0.84
    Activations Density 0.021%

    No Known Activations