© 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. 23757
    Prev
    Next
    INDEX
    Explanations

    phrases indicating instructions or tasks to be done

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "do" and its variations

    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
    rising
    -0.62
    used
    -0.59
    DOC
    -0.58
    rub
    -0.57
    intend
    -0.55
    opened
    -0.54
    books
    -0.54
     Bullets
    -0.53
    mares
    -0.53
    CHAT
    -0.51
    POSITIVE LOGITS
     so
    1.21
     likewise
    0.94
    ze
    0.91
    omsday
    0.90
     away
    0.87
    oming
    0.84
    ggy
    0.82
    ppel
    0.82
    ozy
    0.82
     exactly
    0.80
    Activations Density 0.098%

    No Known Activations