© 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. 10-RES-JB
    11. 6643
    Prev
    Next
    INDEX
    Explanations

    paragraphs discussing problem identification and solution recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning problem-solving techniques and preventative measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.68
    htaking
    -0.67
    prints
    -0.66
    Ranked
    -0.66
     Acquisition
    -0.62
     IMAGES
    -0.61
    omination
    -0.61
     Gleaming
    -0.61
     Subjects
    -0.61
    ivas
    -0.58
    POSITIVE LOGITS
     remedy
    1.83
    Solution
    1.77
     remedies
    1.61
     solutions
    1.52
     solution
    1.51
     workaround
    1.51
     redress
    1.42
     antidote
    1.42
     mitigation
    1.38
     fix
    1.37
    Activations Density 1.187%

    No Known Activations