© 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. 15281
    Prev
    Next
    INDEX
    Explanations

    binary patterns or numerical codes found in text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to sharing or advertisement metrics

    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
    forth
    -0.65
    nown
    -0.63
    jri
    -0.61
     successors
    -0.60
    ortium
    -0.59
     estab
    -0.58
     disg
    -0.57
    Newsletter
    -0.57
     dyn
    -0.56
     remem
    -0.55
    POSITIVE LOGITS
     âĢº
    0.87
     Updated
    0.76
     Transcript
    0.75
     SHARES
    0.72
     ][
    0.70
    Phys
    0.70
     Javascript
    0.66
     Entered
    0.66
    [[
    0.65
    Welcome
    0.64
    Activations Density 0.597%

    No Known Activations