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. 12273
    Prev
    Next
    INDEX
    Explanations

    references to unlimited plans or services

    oai_token-act-pair · gpt-3.5-turbo

    references to unlimited services or features

    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
     Drawn
    -0.85
    acle
    -0.80
    ifice
    -0.75
    emis
    -0.75
    asp
    -0.73
    OB
    -0.72
    acea
    -0.70
    ild
    -0.70
    ector
    -0.70
     Arkham
    -0.69
    POSITIVE LOGITS
     unlimited
    1.15
     access
    0.85
     unrestricted
    0.83
     amounts
    0.81
     roaming
    0.78
    urious
    0.78
     remission
    0.78
     minded
    0.73
     simultane
    0.73
     mobility
    0.70
    Activations Density 0.006%

    No Known Activations