© 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. 0-RES-JB
    11. 1053
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to place names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scra
    -0.63
    Mc
    -0.63
     fades
    -0.63
     TF
    -0.62
     draws
    -0.60
     project
    -0.59
     regist
    -0.58
     retract
    -0.58
     stud
    -0.58
     Hig
    -0.57
    POSITIVE LOGITS
    onia
    4.82
    onian
    2.31
    onic
    1.78
    onica
    1.56
    onics
    1.52
    olia
    1.51
    phia
    1.38
    ony
    1.30
    oni
    1.30
    onite
    1.28
    Activations Density 0.012%

    No Known Activations