© 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. 22623
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and community involvement

    oai_token-act-pair · gpt-3.5-turbo

    references to donations and charitable activities

    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
     theirs
    -0.82
    Certainly
    -0.76
    example
    -0.74
    Indeed
    -0.73
    .�
    -0.72
    Prim
    -0.70
    Obviously
    -0.70
    Exit
    -0.68
    .</
    -0.68
    Parameter
    -0.68
    POSITIVE LOGITS
     curfew
    0.71
     crem
    0.70
     detox
    0.67
     funeral
    0.66
     audits
    0.66
     funer
    0.65
     sexually
    0.65
    £ı
    0.64
     nurses
    0.64
     condom
    0.64
    Activations Density 0.717%

    No Known Activations