© 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. 11-RES-JB
    11. 11646
    Prev
    Next
    INDEX
    Explanations

    statistics and comparisons related to likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    statements relating to probability or likelihood comparisons among different groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.59
    \\\\\\\\\\\\\\\\
    -0.57
    loo
    -0.57
     Outbreak
    -0.57
    Bloom
    -0.56
    ight
    -0.56
    Bit
    -0.56
    ificial
    -0.55
    ights
    -0.55
    pection
    -0.53
    POSITIVE LOGITS
     than
    1.03
     to
    0.90
     prone
    0.76
     respondents
    0.72
     Than
    0.71
    than
    0.65
     dissatisfied
    0.65
     inclined
    0.61
     responders
    0.61
    phrine
    0.60
    Activations Density 0.055%

    No Known Activations