© 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. 8-RES-JB
    11. 2520
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities ending in 'ide', 'ise', or 'ave'

    oai_token-act-pair · gpt-3.5-turbo

    words related to ideologies or philosophical concepts

    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
    etheless
    -0.76
    ãĤ¢ãĥ«
    -0.68
    selves
    -0.65
    ourcing
    -0.65
    INGTON
    -0.65
    iosity
    -0.64
    circ
    -0.63
    matically
    -0.63
    ilateral
    -0.61
    uitous
    -0.60
    POSITIVE LOGITS
    lla
    1.46
    lli
    1.45
    ño
    1.42
    llo
    1.38
    lda
    1.31
    gger
    1.29
    cki
    1.25
    aux
    1.24
    cker
    1.23
    xt
    1.21
    Activations Density 0.349%

    No Known Activations