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. 6242
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns related to a downward or negative trend

    oai_token-act-pair · gpt-3.5-turbo

    present participles and gerunds, particularly those indicating ongoing actions or processes

    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
    ufact
    -1.02
    vironment
    -0.64
    etimes
    -0.63
    ilies
    -0.62
    iston
    -0.62
     pulp
    -0.61
    unts
    -0.61
    ccess
    -0.61
    PLIC
    -0.60
     sust
    -0.59
    POSITIVE LOGITS
    peed
    0.88
    adia
    0.83
    cycles
    0.82
    abouts
    0.80
    cffffcc
    0.79
    shaped
    0.79
    agonal
    0.75
    adesh
    0.75
     downwards
    0.74
     hither
    0.73
    Activations Density 0.149%

    No Known Activations