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

    Neuronpedia

    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. 1509
    Prev
    Next
    INDEX
    Explanations

    phrases related to unspecified outcomes or situations, often followed by speculation or commentary

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or conditionality

    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
    vati
    -0.70
    aza
    -0.69
    livious
    -0.68
    és
    -0.67
    odore
    -0.66
    sha
    -0.64
    ertodd
    -0.64
     Berk
    -0.64
    ALLY
    -0.63
    ridor
    -0.63
    POSITIVE LOGITS
     faults
    0.70
     misc
    0.68
    pires
    0.68
    acity
    0.66
     ç¥ŀ
    0.65
     whims
    0.65
     preach
    0.65
     preached
    0.65
     wishes
    0.65
    aign
    0.63
    Activations Density 0.129%

    No Known Activations