© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    technical details like measurements, dates, and stats

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to people or items

    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
    andowski
    -0.85
     suprem
    -0.81
    iasm
    -0.78
    atars
    -0.75
    conservancy
    -0.72
    ¬¼
    -0.72
    kef
    -0.72
    nik
    -0.71
    rex
    -0.71
    achev
    -0.71
    POSITIVE LOGITS
     hrs
    0.81
     1280
    0.79
     TBA
    0.75
     avg
    0.75
     126
    0.74
     336
    0.70
     208
    0.69
     CLR
    0.69
     TBD
    0.67
     158
    0.67
    Activations Density 0.414%

    No Known Activations