© 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. 0-RES-JB
    6. 6311
    Prev
    Next
    INDEX
    Explanations

    terms related to focus or concentration

    oai_token-act-pair · gpt-3.5-turbo

    references to being concentrated or directed towards a specific goal or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rule
    -0.82
    oti
    -0.70
    illet
    -0.70
     receipt
    -0.67
    fax
    -0.67
     misfortune
    -0.66
    morrow
    -0.63
    edom
    -0.63
     Anthrop
    -0.62
     Barcl
    -0.62
    POSITIVE LOGITS
     focused
    3.44
     foc
    2.59
     focusing
    2.20
    focused
    2.11
     focus
    2.07
     centered
    2.04
    ocused
    2.02
     focuses
    2.00
     concentrated
    1.89
     unfocused
    1.80
    Activations Density 0.014%

    No Known Activations