© 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. 16271
    Prev
    Next
    INDEX
    Explanations

    phrases that include mixed characters and different languages

    oai_token-act-pair · gpt-3.5-turbo

    specific non-English characters or symbols

    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
    Magazine
    -0.67
     trickle
    -0.66
     unforeseen
    -0.65
     fringe
    -0.63
     relegation
    -0.62
     bombshell
    -0.61
     bankruptcy
    -0.60
     clipping
    -0.60
     Standards
    -0.59
     cosmetics
    -0.59
    POSITIVE LOGITS
    É
    1.61
    ËĪ
    1.41
    Äĵ
    1.33
    Ë
    1.30
    Ä«
    1.24
    Äģ
    1.19
    Åį
    1.18
    Ê
    1.15
    Ì
    1.13
    Ç
    1.09
    Activations Density 0.083%

    No Known Activations