© 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. 5873
    Prev
    Next
    INDEX
    Explanations

    lists of groups of people or items

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or collections of individuals or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    owe
    -0.75
    meet
    -0.72
    Ĥİ
    -0.72
    Sexual
    -0.70
    imil
    -0.69
    oslav
    -0.68
    ike
    -0.67
    Viol
    -0.66
    oshi
    -0.66
    osterone
    -0.64
    POSITIVE LOGITS
     assorted
    1.31
     a
    1.08
     two
    1.02
     an
    1.02
     another
    1.00
     some
    1.00
     plenty
    1.00
     several
    0.99
     optionally
    0.93
     three
    0.93
    Activations Density 0.453%

    No Known Activations