Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23571
    Prev
    Next
    INDEX
    Explanations

    names ending in "yer"

    oai_token-act-pair · gpt-3.5-turbo

    words related to lawyer or legal professions

    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
    ivia
    -0.81
    اÙĦ
    -0.80
    drawn
    -0.71
    OPS
    -0.69
    ories
    -0.67
    rongh
    -0.64
     unsupported
    -0.62
    ores
    -0.62
    auri
    -0.62
    owered
    -0.62
    POSITIVE LOGITS
    stein
    0.88
    yer
    0.86
    holm
    0.86
    chell
    0.81
    strom
    0.78
    quist
    0.76
    rors
    0.76
    loo
    0.75
    hood
    0.74
     Myster
    0.73
    Activations Density 0.018%

    No Known Activations