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. 0-RES-JB
    6. 10524
    Prev
    Next
    INDEX
    Explanations

    the phrase "Deep" followed by a single-digit or double-digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to "Deep Space Nine" and related cultural works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bicycl
    -0.82
     bicycle
    -0.81
    resp
    -0.76
    iu
    -0.74
    HCR
    -0.74
     bicycles
    -0.71
    usable
    -0.69
    á¸
    -0.68
     lett
    -0.65
    lag
    -0.64
    POSITIVE LOGITS
     Deep
    3.83
    Deep
    3.02
    deep
    2.31
     deep
    1.80
     deepest
    1.20
     Depth
    1.11
     deeper
    1.10
     depths
    1.06
     deepening
    1.02
     Wide
    0.99
    Activations Density 0.014%

    No Known Activations