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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 9446
    Prev
    Next
    INDEX
    Explanations

    names of places or people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names of places and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccording
    -0.89
     pregn
    -0.76
     conflic
    -0.76
     unden
    -0.67
     indisp
    -0.66
     pestic
    -0.66
    ntil
    -0.64
     pse
    -0.63
    ãĥª
    -0.62
     citiz
    -0.61
    POSITIVE LOGITS
    ville
    0.91
    hurst
    0.89
    burgh
    0.87
    berg
    0.85
    hill
    0.85
    dale
    0.84
     County
    0.83
    ieri
    0.81
    hyde
    0.80
    stown
    0.80
    Activations Density 0.767%

    No Known Activations