© 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. 8-RES-JB
    11. 14809
    Prev
    Next
    INDEX
    Explanations

    informative statements or statistics

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the letter 'O'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CoC
    -0.71
     unfocusedRange
    -0.68
     Yel
    -0.68
     substitutes
    -0.67
    yards
    -0.66
     CRC
    -0.66
     sinks
    -0.66
     wip
    -0.65
     PLA
    -0.65
     CTR
    -0.64
    POSITIVE LOGITS
    ceans
    1.32
    lymp
    1.30
    culus
    1.29
    vernight
    1.22
    scill
    1.21
    mega
    1.11
    tto
    1.11
    rient
    1.11
    ppo
    1.10
    liv
    1.09
    Activations Density 0.034%

    No Known Activations