© 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. 23585
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority or matters of importance

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or subject, particularly the word "the."

    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
    代
    -0.69
     yours
    -0.66
    ÃĥÃĤ
    -0.66
    ãĤĭ
    -0.63
     theirs
    -0.62
    rily
    -0.60
    ornings
    -0.60
    ãĥ¼ãĥĨ
    -0.60
    ãĤ´ãĥ³
    -0.59
    AMI
    -0.59
    POSITIVE LOGITS
    oret
    0.74
     foregoing
    0.73
     authors
    0.72
     discrepancy
    0.71
    resa
    0.69
     vast
    0.68
     relationship
    0.67
     presence
    0.67
     proposed
    0.66
     situation
    0.66
    Activations Density 0.645%

    No Known Activations