© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24146
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artney
    -0.73
    poon
    -0.62
    ilaterally
    -0.62
    noxious
    -0.62
    sg
    -0.62
    solete
    -0.62
    itted
    -0.61
    nih
    -0.60
    âĹ¼
    -0.59
    avored
    -0.59
    POSITIVE LOGITS
     is
    1.25
     lies
    1.14
     isn
    1.13
     arises
    1.13
     here
    1.01
     resides
    0.94
     remains
    0.89
     comes
    0.88
     persists
    0.87
     though
    0.87
    Activations Density 0.124%

    No Known Activations