© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21371
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific concepts or technical details

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or categories such as companies, groups, and phenomena

    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
     positives
    -0.83
     regrets
    -0.79
    issues
    -0.70
    izons
    -0.70
    comments
    -0.69
    illard
    -0.68
    endars
    -0.66
     wounds
    -0.66
     reminders
    -0.66
    auntlets
    -0.64
    POSITIVE LOGITS
     called
    1.94
     named
    1.73
     Called
    1.64
    called
    1.53
     dubbed
    1.52
     known
    1.50
     termed
    1.46
     nicknamed
    1.36
     titled
    1.32
    named
    1.26
    Activations Density 0.550%

    No Known Activations