© 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. 20394
    Prev
    Next
    INDEX
    Explanations

    project names or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to projects, initiatives, and collaborations related to business and community

    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
    aples
    -0.77
     elsewhere
    -0.69
     residues
    -0.66
    abal
    -0.65
     receipt
    -0.64
     mistress
    -0.64
    amba
    -0.63
    eryl
    -0.62
    inventoryQuantity
    -0.61
     residue
    -0.60
    POSITIVE LOGITS
     aims
    1.09
     curated
    0.98
     aimed
    0.92
     collabor
    0.90
    Insp
    0.90
     Inspired
    0.90
     strives
    0.87
     empowering
    0.87
     aim
    0.85
     innovative
    0.84
    Activations Density 0.526%

    No Known Activations