© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a cooking recipe

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence endings in a recipe or instructional context

    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
     barred
    -0.81
     categ
    -0.81
     contradicted
    -0.76
     hijacked
    -0.76
     conflicting
    -0.75
     ridic
    -0.73
     wiser
    -0.72
     haunted
    -0.72
     deserted
    -0.72
     suicidal
    -0.71
    POSITIVE LOGITS
     Repeat
    1.37
     Remove
    1.35
     Slowly
    1.29
     Pour
    1.28
     Then
    1.27
     Transfer
    1.26
     Place
    1.26
     Drain
    1.25
     Divide
    1.24
     Allow
    1.22
    Activations Density 0.075%

    No Known Activations