© 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. 4-RES-JB
    11. 3620
    Prev
    Next
    INDEX
    Explanations

    messages related to interactions with a character named "Bored L.A. Assurance Associate"

    oai_token-act-pair · gpt-3.5-turbo

    words related to boredom

    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
    cel
    -0.71
    ortium
    -0.71
    utable
    -0.70
    itous
    -0.69
    esville
    -0.69
    cellence
    -0.68
    Ĥİ
    -0.67
    imen
    -0.67
    ciation
    -0.67
    asel
    -0.64
    POSITIVE LOGITS
    hower
    0.90
    tsky
    0.90
    dit
    0.78
    MpServer
    0.76
    hole
    0.74
    skirts
    0.73
    66666666
    0.70
    ored
    0.69
    andom
    0.69
    phia
    0.69
    Activations Density 0.014%

    No Known Activations