© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RES-JB
    11. 15415
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities, likely related to locations, organizations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.46
    åĬ
    -0.45
    ividual
    -0.44
    æĢ
    -0.44
    ardless
    -0.43
    together
    -0.42
    ãĤ®
    -0.42
    mentioned
    -0.40
    çĦ
    -0.40
    ãĥį
    -0.40
    POSITIVE LOGITS
    enei
    0.46
    enko
    0.43
     drainage
    0.42
     hostage
    0.42
     fame
    0.42
    aeda
    0.41
     runoff
    0.40
     advis
    0.40
     Syndrome
    0.38
     Corpus
    0.38
    Activations Density 1.984%

    No Known Activations