© 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. 276
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating, collaborating, and influencing positive change, often in organizational or societal contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or agreements involving a specific entity or system

    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
    wheel
    -0.78
    PsyNetMessage
    -0.66
    OME
    -0.63
    itive
    -0.60
     Formation
    -0.59
    Found
    -0.59
    apsed
    -0.58
    numbered
    -0.57
    ULAR
    -0.56
    done
    -0.56
    POSITIVE LOGITS
     satisfies
    1.38
     incorporates
    1.22
     respects
    1.22
     integrates
    1.21
     avoids
    1.20
     resembles
    1.18
     reflects
    1.18
     meets
    1.18
     protects
    1.16
     preserves
    1.14
    Activations Density 0.161%

    No Known Activations