© 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. 2-RES-JB
    11. 3989
    Prev
    Next
    INDEX
    Explanations

    names and terms related to specific individuals in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in the context of notable events or roles

    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
    ropri
    -0.72
    afort
    -0.71
    okemon
    -0.68
    essee
    -0.68
     Colossus
    -0.61
    NetMessage
    -0.60
    insula
    -0.59
    ossession
    -0.58
    enhagen
    -0.58
    imately
    -0.58
    POSITIVE LOGITS
     Wah
    1.04
    renheit
    0.98
    ls
    0.94
    uda
    0.92
    ij
    0.88
    ansen
    0.87
    rite
    0.86
    ua
    0.86
    ida
    0.85
    ttp
    0.85
    Activations Density 0.010%

    No Known Activations