© 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. 1-RES-JB
    11. 24323
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental factors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental concepts and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mammoth
    -0.70
     nap
    -0.67
     deaf
    -0.66
     horn
    -0.65
     gig
    -0.65
     arms
    -0.63
     vicinity
    -0.63
     Scotia
    -0.62
     plant
    -0.62
     fries
    -0.61
    POSITIVE LOGITS
    hip
    1.35
    edIn
    1.32
    ing
    1.32
    ation
    1.17
    ity
    1.09
    al
    1.08
    erness
    1.06
    icipated
    1.05
    ership
    1.05
    eous
    1.02
    Activations Density 0.066%

    No Known Activations