© 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. 8-RES-JB
    11. 11105
    Prev
    Next
    INDEX
    Explanations

    phrases related to removing obstacles or making something clear and unobstructed

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of clearing or removal

    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
    ENTS
    -0.76
    Lenin
    -0.69
     nostalg
    -0.67
    ingo
    -0.65
    sg
    -0.64
    SON
    -0.62
    egal
    -0.61
    sson
    -0.59
    LI
    -0.59
    hips
    -0.59
    POSITIVE LOGITS
     waivers
    0.96
    houses
    0.90
    house
    0.84
     clears
    0.82
    ewater
    0.80
    cloth
    0.76
    ances
    0.76
    cuts
    0.76
    enhagen
    0.75
     cleared
    0.74
    Activations Density 0.037%

    No Known Activations