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. 6-RES-JB
    6. 4887
    Prev
    Next
    INDEX
    Explanations

    keywords related to digital content, such as modes, ads, and data

    oai_token-act-pair · gpt-3.5-turbo

    instances of various interface or navigational elements commonly found in digital environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ded
    -0.71
    yll
    -0.69
     insepar
    -0.64
    ":["
    -0.63
    200000
    -0.60
    gie
    -0.60
     pup
    -0.59
     loudspe
    -0.59
     losers
    -0.58
     distance
    -0.57
    POSITIVE LOGITS
    clair
    0.78
     Interview
    0.69
     Theatre
    0.68
    hammad
    0.67
    counter
    0.67
    Combat
    0.65
    Chart
    0.65
    Click
    0.65
    igible
    0.64
    cart
    0.64
    Activations Density 0.020%

    No Known Activations