© 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. 4-RES-JB
    11. 7878
    Prev
    Next
    INDEX
    Explanations

    references to software development tools, particularly Visual Studio

    oai_token-act-pair · gpt-3.5-turbo

    references to Visual Studio and its associated products or versions

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

    No Comments

    Negative Logits
    cies
    -0.73
    theless
    -0.72
     refere
    -0.70
     tide
    -0.68
     authoritative
    -0.66
    emonic
    -0.66
     constitu
    -0.65
    iscopal
    -0.65
     sacrifice
    -0.65
    umed
    -0.64
    POSITIVE LOGITS
    rait
    0.84
     Studio
    0.83
     Suite
    0.80
     Thumbnails
    0.79
    anus
    0.77
    Lens
    0.76
     Painter
    0.76
    jug
    0.73
    Studio
    0.73
    Works
    0.73
    Activations Density 0.014%

    No Known Activations