© 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. 4-RES-JB
    11. 7309
    Prev
    Next
    INDEX
    Explanations

    the name "Toby" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms associated with the character "Toby" and related variations

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

    No Comments

    Negative Logits
    ional
    -0.81
    krit
    -0.71
    igent
    -0.71
    iment
    -0.69
    ŃĶ
    -0.66
    los
    -0.66
    hips
    -0.66
    ogical
    -0.65
     merit
    -0.64
    ioned
    -0.63
    POSITIVE LOGITS
    oby
    1.12
    ellow
    0.82
    BY
    0.81
    ãĥį
    0.77
    ota
    0.77
    dump
    0.75
    pload
    0.74
    ãĥ³ãĤ¸
    0.73
    ote
    0.72
    utsu
    0.72
    Activations Density 0.010%

    No Known Activations