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. 15490
    Prev
    Next
    INDEX
    Explanations

    time duration phrases mentioning 'two and a half'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to quantities involving "two" and "a half."

    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
    TEXTURE
    -0.77
    NSA
    -0.74
    ACH
    -0.67
    LOCK
    -0.65
    BALL
    -0.64
     STATS
    -0.63
    ATS
    -0.63
    éĹĺ
    -0.63
    ORN
    -0.62
    Reloaded
    -0.62
    POSITIVE LOGITS
     proclamation
    0.65
    aml
    0.64
     thirds
    0.62
     wife
    0.61
     couple
    0.60
     groceries
    0.59
     mates
    0.58
     return
    0.58
     consequ
    0.58
    teenth
    0.57
    Activations Density 0.082%

    No Known Activations