© 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. 1017
    Prev
    Next
    INDEX
    Explanations

    the given name "Nicolas."

    oai_token-act-pair · gpt-4-turbo

    references to names, particularly the name "Nicolas."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nicolas" and its variations, indicating a focus on that individual

    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
     Tacoma
    -0.85
    edom
    -0.83
     Norton
    -0.75
     Vive
    -0.74
     Examiner
    -0.69
     guiActiveUnfocused
    -0.69
    DERR
    -0.69
    plain
    -0.69
     Isle
    -0.68
    EEP
    -0.67
    POSITIVE LOGITS
    otine
    1.11
    cer
    0.98
     acid
    0.85
    uana
    0.85
    sis
    0.84
    phal
    0.84
    uity
    0.83
    oshenko
    0.81
    uez
    0.79
    stal
    0.78
    Activations Density 0.017%

    No Known Activations