© 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. 15897
    Prev
    Next
    INDEX
    Explanations

    words related to stars

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stars and celestial bodies

    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
    ĸļ
    -0.76
    ĵĺ
    -0.72
    odcast
    -0.70
    uthor
    -0.69
    ãĥ¼ãĥ³
    -0.68
    ibaba
    -0.66
    IGH
    -0.63
     Neurolog
    -0.62
     LIA
    -0.62
    ahon
    -0.62
    POSITIVE LOGITS
    hips
    1.33
    burst
    1.26
    cream
    1.18
    light
    1.14
    lit
    0.99
    fish
    0.97
    stru
    0.97
    bucks
    0.96
    fighter
    0.90
    lite
    0.85
    Activations Density 0.028%

    No Known Activations