Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20085
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming, specifically related to following a line in a computer game while dodging objects

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.77
    ographers
    -0.71
    ourge
    -0.71
    paio
    -0.70
    antes
    -0.67
     ions
    -0.67
    onite
    -0.65
    addafi
    -0.65
    izons
    -0.64
     outweigh
    -0.64
    POSITIVE LOGITS
     guise
    1.07
     nutshell
    1.03
     midst
    0.90
     context
    0.83
     manner
    0.82
     whirlwind
    0.78
     mode
    0.75
     vicinity
    0.71
     periphery
    0.71
     fashion
    0.70
    Activations Density 1.402%

    No Known Activations