© 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. 7-RES-JB
    11. 2223
    Prev
    Next
    INDEX
    Explanations

    website links and URLs

    oai_token-act-pair · gpt-3.5-turbo

    instances of ellipses or truncation in text

    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
    entimes
    -0.83
     suspic
    -0.81
     wielded
    -0.79
     Lomb
    -0.72
     nodd
    -0.68
     tampering
    -0.67
    Ļ½
    -0.67
     diminishing
    -0.67
    irens
    -0.66
     choke
    -0.66
    POSITIVE LOGITS
     âĢİ
    0.92
    Done
    0.85
    =#
    0.75
    Delivery
    0.73
    prop
    0.72
    rock
    0.72
    itect
    0.72
    BRE
    0.70
    etc
    0.70
    abil
    0.69
    Activations Density 0.030%

    No Known Activations