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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 11815
    Prev
    Next
    INDEX
    Explanations

    patterns related to hexadecimal values

    oai_token-act-pair · gpt-3.5-turbo

    references to the age group 65 and older

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -0.82
    uyomi
    -0.78
     tension
    -0.77
    yout
    -0.74
    pressure
    -0.74
    */(
    -0.74
    mble
    -0.73
    iya
    -0.71
    yang
    -0.71
    yers
    -0.70
    POSITIVE LOGITS
     ILCS
    1.61
    328
    1.05
    65
    1.00
    ENCY
    0.94
    67
    0.87
    ONT
    0.86
    625
    0.85
    630
    0.84
    66
    0.83
    _.
    0.83
    Activations Density 0.021%

    No Known Activations