© 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. 4-RES-JB
    11. 6947
    Prev
    Next
    INDEX
    Explanations

    phrases indicating admiration and taking a chance on something

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant revelations or unveilings

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

    No Comments

    Negative Logits
     vet
    -0.71
     Fever
    -0.69
    naires
    -0.67
    iasis
    -0.61
     Anxiety
    -0.61
    schild
    -0.59
     glossy
    -0.59
    anmar
    -0.59
    VPN
    -0.58
     psy
    -0.58
    POSITIVE LOGITS
    yss
    0.80
    âĹ¼
    0.75
    ij士
    0.74
    ©¶æ
    0.74
    ãĤ¤ãĥĪ
    0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.64
    \/\/
    0.64
    ensor
    0.63
     secondly
    0.63
    rium
    0.62
    Activations Density 0.000%

    No Known Activations