© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1598
    Prev
    Next
    INDEX
    Explanations

    phrases where actions or achievements are associated with specific groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word 'with' and related phrases indicating association or accompaniment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chan
    -0.71
    obi
    -0.70
    former
    -0.69
    affected
    -0.67
    late
    -0.67
    obook
    -0.64
    ondo
    -0.64
    icator
    -0.63
    SPONSORED
    -0.63
    strate
    -0.63
    POSITIVE LOGITS
     regards
    1.35
     regard
    1.29
    draw
    1.05
     impunity
    1.00
     respect
    0.94
    standing
    0.92
    holding
    0.84
    stood
    0.82
     vig
    0.81
    drawn
    0.76
    Activations Density 0.171%

    No Known Activations