© 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. 2-RES-JB
    11. 529
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4-turbo

    names of famous individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRES
    -0.54
     behalf
    -0.54
    tnc
    -0.49
     hers
    -0.48
    venge
    -0.48
     theirs
    -0.47
    Scotland
    -0.47
    )).
    -0.46
    76561
    -0.44
    VIDEO
    -0.44
    POSITIVE LOGITS
    ogether
    0.58
    arten
    0.56
    bnb
    0.56
    querque
    0.53
    ortun
    0.53
     however
    0.51
     lasted
    0.51
    arij
    0.51
    emonium
    0.51
     assigns
    0.50
    Activations Density 5.606%

    No Known Activations