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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7231
    Prev
    Next
    INDEX
    Explanations

    the name "Benedict" at varying strengths

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, particularly those in positions of power or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAY
    -0.90
    WAYS
    -0.90
    ULT
    -0.89
    PER
    -0.84
    MIC
    -0.82
    BLE
    -0.78
    DAQ
    -0.74
    matically
    -0.74
    Ko
    -0.74
    matic
    -0.74
    POSITIVE LOGITS
     Cumber
    1.05
    shire
    0.97
    itude
    0.90
     Schwarzenegger
    0.85
     XVI
    0.85
    éĹĺ
    0.81
    ured
    0.80
    ieth
    0.79
    sson
    0.78
    rophic
    0.75
    Activations Density 0.032%

    No Known Activations