© 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. 0-RES-JB
    11. 19567
    Prev
    Next
    INDEX
    Explanations

    words related to a specific type of plant that is often associated with domestication and evolution

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to specific types of plants and their cultural or functional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alchemist
    -0.71
    Rog
    -0.69
     Coff
    -0.68
     Ferry
    -0.68
     Legislative
    -0.67
    LED
    -0.67
     Genius
    -0.66
     Proposition
    -0.65
     Nicotine
    -0.65
     Bowman
    -0.64
    POSITIVE LOGITS
     squash
    2.03
     pac
    1.80
    pac
    1.37
     unite
    1.10
     greens
    1.09
    kos
    1.06
     relay
    1.00
     Ivy
    0.94
    itans
    0.93
     raced
    0.92
    Activations Density 0.077%

    No Known Activations