© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 23700
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculation or prediction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe potential appearances or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osi
    -0.60
    signed
    -0.59
     Quit
    -0.57
    moon
    -0.54
    tap
    -0.54
     detectives
    -0.54
     Fever
    -0.53
    arms
    -0.53
    vette
    -0.53
     mention
    -0.52
    POSITIVE LOGITS
     unfolding
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.74
    falls
    0.72
    urities
    0.71
    nings
    0.71
    ãĤ´
    0.67
    Ô
    0.65
    abouts
    0.65
     GOODMAN
    0.64
     versus
    0.63
    Activations Density 0.220%

    No Known Activations