© 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. 9-RES-JB
    11. 9189
    Prev
    Next
    INDEX
    Explanations

    phrases related to quality, completeness, and improvements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparisons and contrasts between elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scrib
    -0.89
    »Ĵ
    -0.87
    iatus
    -0.85
    ģĸ
    -0.84
    ndum
    -0.82
    quished
    -0.82
    zan
    -0.79
    ð
    -0.78
    aunder
    -0.78
    ascist
    -0.78
    POSITIVE LOGITS
     aesthetics
    1.44
     usability
    1.23
     gameplay
    1.23
     layout
    1.20
     texture
    1.19
     aesthetic
    1.19
     performance
    1.18
     styling
    1.15
     visuals
    1.15
     presentation
    1.12
    Activations Density 0.545%

    No Known Activations