© 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. 7649
    Prev
    Next
    INDEX
    Explanations

    phrases involving statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    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
    contained
    -0.75
    ounces
    -0.75
    thood
    -0.72
    Ò
    -0.70
    perse
    -0.69
    imi
    -0.69
     resembling
    -0.68
    rehend
    -0.67
     Includes
    -0.66
     overseen
    -0.66
    POSITIVE LOGITS
    oret
    1.60
    resa
    1.32
     downside
    1.23
     easiest
    1.23
     biggest
    1.20
     reason
    1.19
     simplest
    1.17
     irony
    1.15
    ories
    1.14
     problem
    1.13
    Activations Density 0.496%

    No Known Activations