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. 11-RES-JB
    6. 15069
    Prev
    Next
    INDEX
    Explanations

    locations and dates mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" followed by dates or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ographers
    -0.69
     teasp
    -0.67
     destro
    -0.64
    ãĥ¯ãĥ³
    -0.63
    acters
    -0.62
    ographies
    -0.61
    alog
    -0.60
    plin
    -0.59
     withd
    -0.59
     conclud
    -0.57
    POSITIVE LOGITS
     Sept
    1.44
     Feb
    1.43
     Saturday
    1.41
     Aug
    1.41
     Sunday
    1.40
     Wednesday
    1.38
     Nov
    1.37
     Thursday
    1.37
     Tuesday
    1.37
     Friday
    1.35
    Activations Density 0.100%

    No Known Activations