© 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. 10206
    Prev
    Next
    INDEX
    Explanations

    keywords related to runtime processes and memory allocation

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to computer memory management and runtime operations

    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
    ongyang
    -1.06
    essee
    -0.97
    olulu
    -0.92
    Ĭ±
    -0.92
    ippi
    -0.89
    imore
    -0.86
    Ń·
    -0.85
    ouston
    -0.85
    kef
    -0.84
    atche
    -0.82
    POSITIVE LOGITS
     runtime
    0.98
     Runtime
    0.71
    ULT
    0.68
    UX
    0.66
    Exception
    0.66
    runtime
    0.66
     NX
    0.64
    EED
    0.64
    framework
    0.64
    ãĤ§
    0.63
    Activations Density 0.008%

    No Known Activations