© 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. 11-RES-JB
    11. 17551
    Prev
    Next
    INDEX
    Explanations

    phrases related to needs, help, and assistance

    oai_token-act-pair · gpt-3.5-turbo

    needs related to social and community support

    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
    azar
    -0.73
    nown
    -0.73
    otypes
    -0.68
    ocry
    -0.67
    ivably
    -0.66
     errone
    -0.65
    uton
    -0.65
    omin
    -0.64
    ationally
    -0.63
    glomer
    -0.63
    POSITIVE LOGITS
     urgently
    1.12
     clarification
    1.05
     refres
    1.05
     HELP
    0.98
     help
    0.96
     ASAP
    0.96
     reinforcement
    0.95
     reinforcements
    0.94
     guidance
    0.89
     assurance
    0.89
    Activations Density 0.277%

    No Known Activations