© 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. 17416
    Prev
    Next
    INDEX
    Explanations

    information related to the materials something is made from

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the manufacturing or composition of objects

    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
    VERTISEMENT
    -0.72
    RESULTS
    -0.69
     NCT
    -0.66
     Wass
    -0.64
     misses
    -0.61
    Chapter
    -0.61
    SPONSORED
    -0.61
    GREEN
    -0.60
    communications
    -0.60
    Balt
    -0.60
    POSITIVE LOGITS
     entirely
    0.96
     specifically
    0.86
     cheaply
    0.85
     exclusively
    0.82
     chiefly
    0.78
     from
    0.77
     specially
    0.77
     primarily
    0.77
    illet
    0.76
     principally
    0.75
    Activations Density 0.108%

    No Known Activations