© 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. 16596
    Prev
    Next
    INDEX
    Explanations

    terms related to organs in the human body or biological systems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "organ" in various contexts related to both biological and organizational themes

    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
     Enemies
    -0.78
    antage
    -0.75
     squared
    -0.72
     Atk
    -0.70
    mares
    -0.69
    utations
    -0.68
     Surprise
    -0.66
    Tokens
    -0.66
    atts
    -0.66
    uy
    -0.65
    POSITIVE LOGITS
     organ
    4.17
     Organ
    2.05
    organ
    1.91
    Organ
    1.81
     organs
    1.71
     organizer
    1.50
     organic
    1.49
     organised
    1.27
     organising
    1.21
     Organic
    1.09
    Activations Density 0.010%

    No Known Activations