© 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. 2697
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions with a focus on specific symptoms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'o' in various contexts

    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
    REDACTED
    -0.65
     unsupported
    -0.62
     employing
    -0.60
     unspecified
    -0.60
     Newsp
    -0.60
     disparate
    -0.58
    enance
    -0.58
     Crit
    -0.57
     numbering
    -0.56
     naming
    -0.56
    POSITIVE LOGITS
    ppy
    1.15
    pping
    1.14
    pper
    1.13
    gging
    1.12
    opy
    1.09
    ÃŁ
    1.07
    ppo
    1.06
    pped
    1.05
    pless
    1.04
    ppers
    1.03
    Activations Density 0.105%

    No Known Activations