© 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. 11-RES-JB
    11. 18844
    Prev
    Next
    INDEX
    Explanations

    phrases related to solving problems or addressing issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ceremonies
    -0.78
     ceremony
    -0.70
    iazep
    -0.68
     salute
    -0.67
    urch
    -0.65
     Values
    -0.65
     Pledge
    -0.64
     Oath
    -0.64
     oath
    -0.64
    recomm
    -0.63
    POSITIVE LOGITS
     solved
    1.56
     exacerbated
    1.29
    Solution
    1.25
     compounded
    1.24
     insur
    1.18
     unsolved
    1.18
     resolved
    1.15
     plag
    1.13
     systemic
    1.12
     endemic
    1.11
    Activations Density 0.281%

    No Known Activations