© 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. 10-RES-JB
    11. 14153
    Prev
    Next
    INDEX
    Explanations

    verbs related to overriding or ignoring something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dominance and control over situations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.69
     Lauder
    -0.66
     anecd
    -0.65
     Depot
    -0.65
     seeker
    -0.61
     Bei
    -0.59
     è£ıè
    -0.59
    Kit
    -0.58
     Refuge
    -0.58
     idle
    -0.58
    POSITIVE LOGITS
    ighed
    1.06
    idden
    0.96
    xual
    0.95
    ensible
    0.90
    uled
    0.90
    ides
    0.88
    eded
    0.87
    ulation
    0.82
    uing
    0.82
    eding
    0.81
    Activations Density 0.059%

    No Known Activations