© 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. 14819
    Prev
    Next
    INDEX
    Explanations

    the word "way" followed by a number and a comma

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "either way."

    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
     cellul
    -0.64
     resistant
    -0.63
    english
    -0.62
    bent
    -0.61
    coded
    -0.59
    bian
    -0.59
    nered
    -0.59
    illus
    -0.58
     reactive
    -0.58
     instruction
    -0.57
    POSITIVE LOGITS
    cape
    0.81
    ipp
    0.72
    acket
    0.72
     THEN
    0.71
     else
    0.71
     agrees
    0.70
     Regardless
    0.70
    >>>>>>>>
    0.69
     insofar
    0.68
     accepts
    0.68
    Activations Density 0.043%

    No Known Activations