© 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. 23791
    Prev
    Next
    INDEX
    Explanations

    phrases related to reduction or decrease in size or quantity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or decrease in size

    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
    POL
    -0.80
    raid
    -0.74
    ":[{"
    -0.63
    PLIC
    -0.63
    cause
    -0.62
    shows
    -0.62
    role
    -0.61
    iqu
    -0.61
    Pa
    -0.61
     Drama
    -0.61
    POSITIVE LOGITS
    glers
    0.89
    ular
    0.81
     violet
    0.80
    downs
    0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.76
     shrink
    0.75
    lasses
    0.74
    eness
    0.74
     shrinking
    0.74
    abies
    0.74
    Activations Density 0.042%

    No Known Activations