© 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. 17289
    Prev
    Next
    INDEX
    Explanations

    words related to auditing or verification processes

    oai_token-act-pair · gpt-3.5-turbo

    references to auditing-related terms or actions

    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
    ulkan
    -0.78
    ktop
    -0.72
    TON
    -0.69
     Tend
    -0.65
    OPLE
    -0.64
    tons
    -0.64
     Pearce
    -0.62
     AZ
    -0.60
    xual
    -0.60
    terday
    -0.59
    POSITIVE LOGITS
    iov
    1.44
    iences
    1.37
    ience
    1.35
    acious
    1.23
    acity
    1.21
    itors
    1.20
    yssey
    1.13
    iology
    1.12
    iting
    1.12
    ibly
    1.08
    Activations Density 0.039%

    No Known Activations