© 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. 21235
    Prev
    Next
    INDEX
    Explanations

    technical issues and problems mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bugs and technical issues

    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
    STON
    -0.85
    augh
    -0.82
    prise
    -0.80
    shall
    -0.75
    oral
    -0.74
    ategic
    -0.73
    forts
    -0.73
    orthy
    -0.72
    heid
    -0.72
    aughter
    -0.71
    POSITIVE LOGITS
     inability
    1.18
     improperly
    1.11
     faulty
    1.05
     insufficient
    1.05
     inconsistent
    1.01
     improper
    1.01
     Unable
    1.01
     inconsistency
    1.01
     incorrect
    0.98
     unreliable
    0.97
    Activations Density 0.492%

    No Known Activations