© 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. 9-RES-JB
    11. 6857
    Prev
    Next
    INDEX
    Explanations

    updates or changes in information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nurture
    -0.71
    sbm
    -0.67
     everyday
    -0.66
     loneliness
    -0.65
    oeuv
    -0.65
    ²¾
    -0.64
    Imagine
    -0.63
    minecraft
    -0.63
     indifferent
    -0.63
    ¥µ
    -0.62
    POSITIVE LOGITS
     corrected
    1.24
     clarification
    1.15
     clarified
    1.14
    UPDATE
    1.03
     corrections
    1.02
     revised
    1.01
     correction
    1.01
     typo
    0.99
    PDATED
    0.99
     Correction
    0.98
    Activations Density 0.402%

    No Known Activations