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. 7-RES-JB
    6. 6969
    Prev
    Next
    INDEX
    Explanations

    sentences indicating lack of clarity or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INT
    -0.83
    zig
    -0.72
    ocard
    -0.71
    jet
    -0.71
    inse
    -0.67
    @#&
    -0.66
    vis
    -0.66
    clerosis
    -0.65
    tha
    -0.65
    tin
    -0.65
    POSITIVE LOGITS
     whether
    0.86
     how
    0.74
     jurisdiction
    0.74
    ether
    0.73
     quantity
    0.71
    abouts
    0.67
    ly
    0.66
     why
    0.65
    eth
    0.64
    ively
    0.63
    Activations Density 0.032%

    No Known Activations