© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    words that introduce actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intent or purpose

    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
    pict
    -0.71
     Appears
    -0.70
     traded
    -0.60
    calling
    -0.60
    itates
    -0.58
    AAAAAAAA
    -0.57
    cards
    -0.56
     disappeared
    -0.56
     forg
    -0.56
    comments
    -0.56
    POSITIVE LOGITS
     summarize
    1.28
    ilet
    1.28
     complicate
    1.27
     illustrate
    1.23
     maximize
    1.19
     accomplish
    1.17
     achieve
    1.16
     facilitate
    1.14
     compensate
    1.14
     reiterate
    1.12
    Activations Density 0.047%

    No Known Activations