© 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. 7-RES-JB
    11. 1644
    Prev
    Next
    INDEX
    Explanations

    evaluative statements on a scale

    oai_token-act-pair · gpt-3.5-turbo

    quality ratings on a defined scale

    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
    ateurs
    -0.58
     kios
    -0.55
     frontline
    -0.54
     mosqu
    -0.52
     pamph
    -0.52
    rollers
    -0.52
     busy
    -0.51
     café
    -0.51
     webcam
    -0.50
     malls
    -0.50
    POSITIVE LOGITS
     applicable
    0.61
     Definition
    0.57
     coefficients
    0.56
    worthiness
    0.55
     criteria
    0.54
    Definition
    0.52
     severity
    0.52
     dB
    0.52
    cellence
    0.52
     affirmative
    0.52
    Activations Density 1.197%

    No Known Activations