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. 9282
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numeric dates and times associated with events

    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
     Wem
    -0.68
    ãĥ¼ãĥĨ
    -0.65
     incidentally
    -0.63
    ichick
    -0.62
    keeper
    -0.61
    llular
    -0.60
     absor
    -0.60
     myself
    -0.59
    prisingly
    -0.59
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    POSITIVE LOGITS
    LOS
    1.13
    SHARE
    1.09
    WASHINGTON
    1.05
    Authorities
    0.96
    BAT
    0.93
    SAN
    0.93
    PROV
    0.92
    PORT
    0.90
    NEW
    0.89
    Police
    0.86
    Activations Density 0.150%

    No Known Activations