© 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. 9-RES-JB
    11. 20767
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement or alignment

    oai_token-act-pair · gpt-3.5-turbo

    statements and assertions about equivalence or similarity across different subjects or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zos
    -0.73
    ded
    -0.60
    watch
    -0.59
    ichen
    -0.55
    urat
    -0.54
     interrupts
    -0.54
    ffff
    -0.54
    stru
    -0.53
    agram
    -0.52
    NetMessage
    -0.52
    POSITIVE LOGITS
    ï¸ı
    0.83
     Nationwide
    0.71
     everywhere
    0.66
    unity
    0.64
    pn
    0.63
    ivism
    0.62
    oat
    0.62
     applies
    0.61
    sburgh
    0.61
    blance
    0.61
    Activations Density 0.188%

    No Known Activations