© 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. 8-RES-JB
    11. 2714
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "coral" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leck
    -0.76
    endor
    -0.71
    lihood
    -0.70
    uyomi
    -0.66
     Honour
    -0.66
     Genius
    -0.65
     Generation
    -0.64
     Disorder
    -0.61
     Order
    -0.61
    sburgh
    -0.60
    POSITIVE LOGITS
    nered
    1.05
    nea
    0.96
    alling
    0.88
    ebook
    0.87
    gi
    0.84
    alled
    0.83
    ocular
    0.83
    bons
    0.82
    aling
    0.82
    ping
    0.81
    Activations Density 0.025%

    No Known Activations