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. 1144
    Prev
    Next
    INDEX
    Explanations

    phrases related to slowness

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the term "slow."

    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
    ortium
    -1.03
    vironment
    -0.84
    çīĪ
    -0.82
    ilitary
    -0.79
    amara
    -0.76
    incerity
    -0.76
    rists
    -0.76
    iosyncr
    -0.75
    uably
    -0.74
    pheus
    -0.74
    POSITIVE LOGITS
     cooker
    1.14
     paced
    1.10
    downs
    1.04
    est
    0.95
    poke
    0.94
     pace
    0.89
     slow
    0.85
    down
    0.85
     speeds
    0.83
     Slow
    0.81
    Activations Density 0.017%

    No Known Activations