© 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. 7-RES-JB
    11. 21138
    Prev
    Next
    INDEX
    Explanations

    parentheses that contain explanatory or qualifying information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically closing parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.75
     (=
    -0.68
     ($
    -0.66
    arus
    -0.66
    (&
    -0.65
     (âĪĴ
    -0.65
     (%
    -0.65
     (
    -0.65
     (~
    -0.65
    (
    -0.63
    POSITIVE LOGITS
    ACTED
    0.70
    ãĥİ
    0.65
    famous
    0.59
    arthed
    0.59
    ATURE
    0.58
    interest
    0.56
    multiple
    0.56
     Gamb
    0.56
    TPS
    0.55
     Malf
    0.55
    Activations Density 0.098%

    No Known Activations