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. 19960
    Prev
    Next
    INDEX
    Explanations

    proper names with an apostrophe

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'O' followed by a single quote

    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
    vg
    -0.79
     eclipse
    -0.74
     incent
    -0.68
     thrill
    -0.67
     academics
    -0.67
    anwhile
    -0.66
    »Ĵ
    -0.63
    iae
    -0.62
    asers
    -0.62
    OPLE
    -0.62
    POSITIVE LOGITS
    Brien
    1.08
    Neill
    1.01
    Connor
    1.00
    Malley
    0.97
    Donnell
    0.94
    clock
    0.92
    Leary
    0.91
    Reilly
    0.85
    Sullivan
    0.82
    Tel
    0.79
    Activations Density 0.015%

    No Known Activations