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. 16983
    Prev
    Next
    INDEX
    Explanations

    instances where the word "very" is used in a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "very" in conjunction with variations of context or conditions

    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
    olor
    -0.76
    orno
    -0.74
    onis
    -0.73
    fu
    -0.71
    VL
    -0.71
    atown
    -0.68
    ensis
    -0.66
    zilla
    -0.66
    vertising
    -0.66
    imus
    -0.66
    POSITIVE LOGITS
     opposite
    0.77
     naughty
    0.71
     undefined
    0.70
     fertile
    0.68
     Reverend
    0.68
     same
    0.67
     logical
    0.67
     antit
    0.66
     poorest
    0.66
     unfortunate
    0.66
    Activations Density 0.041%

    No Known Activations