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. 7-RES-JB
    6. 4381
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or names, such as 'Rolling Stone' and 'Jackie'

    oai_token-act-pair · gpt-3.5-turbo

    references to the publication "Rolling Stone" and the name "Jackie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sense
    -0.93
    leneck
    -0.78
    uchin
    -0.75
    anyahu
    -0.74
    lessly
    -0.74
    sky
    -0.73
    netflix
    -0.73
    nil
    -0.73
    esc
    -0.73
    earing
    -0.72
    POSITIVE LOGITS
     Stones
    1.04
     Stone
    0.85
     Rolling
    0.80
     Browne
    0.75
    pled
    0.74
     Jackie
    0.65
    Stone
    0.65
     Rican
    0.65
     Vie
    0.64
     Tire
    0.64
    Activations Density 0.041%

    No Known Activations