© 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. 9041
    Prev
    Next
    INDEX
    Explanations

    locations, names, and titles with a mix of lowercase and special characters

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with global issues and important events

    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
     predec
    -0.62
     referen
    -0.61
     corrid
    -0.60
    vertisement
    -0.59
     destro
    -0.58
    ãĥ¯ãĥ³
    -0.58
     scrut
    -0.57
    ÃĥÃĤ
    -0.57
     challeng
    -0.56
    âĸ¬
    -0.55
    POSITIVE LOGITS
     âĵĺ
    0.66
     Phant
    0.58
    utics
    0.58
     Dism
    0.57
     Houth
    0.54
     Profile
    0.52
     Fract
    0.51
     AST
    0.51
     Thy
    0.50
    .--
    0.49
    Activations Density 1.187%

    No Known Activations