Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8041
    Prev
    Next
    INDEX
    Explanations

    statements related to astronomical research

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or conclusions in the text

    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
     discretion
    -0.89
     abuser
    -0.86
     prosec
    -0.84
     abused
    -0.84
     negoti
    -0.84
     attrition
    -0.84
     boycot
    -0.82
     absentee
    -0.82
     vigilante
    -0.82
     recru
    -0.82
    POSITIVE LOGITS
    NASA
    1.84
    Scientists
    1.69
     Astron
    1.65
     Scientists
    1.61
    Ast
    1.49
     NASA
    1.47
     Planetary
    1.46
     Nasa
    1.46
     Hubble
    1.41
     astronomers
    1.40
    Activations Density 0.262%

    No Known Activations