© 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. 2-RES-JB
    11. 8430
    Prev
    Next
    INDEX
    Explanations

    terms related to technical or programming contexts, particularly focusing on the concept of "static."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to static characteristics or qualities

    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
    orney
    -0.88
    vest
    -0.85
     GOODMAN
    -0.84
    chen
    -0.80
    ï¸
    -0.76
    furt
    -0.76
    amins
    -0.76
    arenthood
    -0.75
    ñ
    -0.75
    ishops
    -0.74
    POSITIVE LOGITS
     static
    0.83
     electricity
    0.80
     upkeep
    0.79
     inline
    0.74
     reactive
    0.71
    iple
    0.70
     diffusion
    0.69
     emission
    0.68
     tac
    0.68
     recoil
    0.68
    Activations Density 0.007%

    No Known Activations