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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 24369
    Prev
    Next
    INDEX
    Explanations

    comparisons between different time periods or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparisons between different time periods or generations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    press
    -0.66
     promptly
    -0.66
     accordingly
    -0.65
     ASAP
    -0.64
    details
    -0.63
     thanked
    -0.63
    urai
    -0.60
    osterone
    -0.59
     teamed
    -0.56
     wondered
    -0.56
    POSITIVE LOGITS
    outer
    0.84
    emouth
    0.76
    ahime
    0.73
    animate
    0.72
    anyl
    0.71
     previous
    0.70
     predecessors
    0.69
    nings
    0.67
     sidx
    0.65
    ppo
    0.64
    Activations Density 0.198%

    No Known Activations