© 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 EvalsExportsinterp-engineNEWAPI 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. 24255
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use the word "like" to make comparisons or draw analogies

    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
    inas
    -0.79
    elin
    -0.75
    aptic
    -0.72
    xious
    -0.71
    endiary
    -0.71
    Published
    -0.68
    overy
    -0.67
    erial
    -0.65
    inion
    -0.65
    ourse
    -0.65
    POSITIVE LOGITS
    lihood
    1.56
    liest
    1.18
    lier
    1.17
     ours
    1.04
    liness
    0.92
     minded
    0.92
    minded
    0.89
     theirs
    0.80
     yours
    0.80
     wildfire
    0.74
    Activations Density 0.072%

    No Known Activations