© 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. 24069
    Prev
    Next
    INDEX
    Explanations

    specific activating sequences of special characters

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions and personal reflections

    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
     payroll
    -0.83
     orchestr
    -0.83
     frontline
    -0.82
     displacement
    -0.80
     phased
    -0.80
     funnel
    -0.80
     aggreg
    -0.79
     dubbed
    -0.77
     brid
    -0.76
     negoti
    -0.75
    POSITIVE LOGITS
    Anyway
    1.48
    Advertisements
    1.45
    Reply
    1.41
    Reviewer
    1.37
    âĿ
    1.31
    RAW
    1.30
    Loading
    1.28
    âĶĢâĶĢâĶĢâĶĢ
    1.26
    Trivia
    1.21
    --------------------------------------------------------
    1.21
    Activations Density 0.395%

    No Known Activations