© 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. 6677
    Prev
    Next
    INDEX
    Explanations

    solutions or strategies for various conflicts and scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate solutions to societal issues or conflicts

    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
    Ire
    -0.71
    ãĥĥãĥī
    -0.71
    arton
    -0.59
     Instr
    -0.57
    ãģĦ
    -0.56
     notor
    -0.55
    ratch
    -0.54
    Ĭ±
    -0.51
    qus
    -0.50
     predec
    -0.49
    POSITIVE LOGITS
     awaits
    1.10
     emerges
    0.84
     greets
    0.80
    Joined
    0.77
     consisting
    0.75
     featuring
    0.74
     ensued
    0.73
     accompanies
    0.73
    !!!!
    0.73
     arrives
    0.72
    Activations Density 0.637%

    No Known Activations