© 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. 3624
    Prev
    Next
    INDEX
    Explanations

    phrases related to constructing or assembling something, particularly in a setting involving imitation or approximation

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases related to deception or trickery

    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
     unfocusedRange
    -0.81
    ourses
    -0.79
    clerosis
    -0.76
     GOODMAN
    -0.76
    ibel
    -0.72
     actionGroup
    -0.72
     RELEASE
    -0.70
    ourse
    -0.70
    IRC
    -0.69
    uve
    -0.68
    POSITIVE LOGITS
    wra
    0.72
     Hats
    0.68
    balls
    0.68
     caric
    0.67
    pas
    0.65
    pants
    0.64
     excuse
    0.63
     hide
    0.62
     whisk
    0.62
    boot
    0.61
    Activations Density 0.215%

    No Known Activations