© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3345
    Prev
    Next
    INDEX
    Explanations

    positive attributes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    expressions that highlight notable or significant aspects of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scl
    -0.83
     actionGroup
    -0.73
    bow
    -0.70
    COL
    -0.69
    tenance
    -0.67
    Cause
    -0.67
    kr
    -0.66
    rift
    -0.66
    cue
    -0.64
    DERR
    -0.63
    POSITIVE LOGITS
     these
    0.82
     this
    0.80
     Kinnikuman
    0.75
     owning
    0.70
     modern
    0.68
     deploying
    0.63
    adding
    0.63
     designing
    0.62
     constructing
    0.62
     Banner
    0.62
    Activations Density 0.160%

    No Known Activations