© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14095
    Prev
    Next
    INDEX
    Explanations

    terms indicating causality or attribution

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and pronouns used to connect statements about actions or observations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ramids
    -0.76
    uku
    -0.74
    iker
    -0.65
    ika
    -0.64
    uli
    -0.63
    mill
    -0.61
    istant
    -0.61
    ventions
    -0.60
     chemistry
    -0.60
    ãĥĥãĥĪ
    -0.60
    POSITIVE LOGITS
    rouse
    0.84
     mattered
    0.79
     prompted
    0.75
     Guinness
    0.73
     distinguishes
    0.70
     bothers
    0.69
     sshd
    0.69
     determines
    0.67
    dn
    0.67
     transc
    0.65
    Activations Density 0.108%

    No Known Activations