Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19442
    Prev
    Next
    INDEX
    Explanations

    occurrences of the number 70 or percentages close to it

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the quantity or percentage of 70

    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
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    ĪĴ
    -0.72
    iton
    -0.64
    staking
    -0.63
     Cind
    -0.63
     Des
    -0.63
    den
    -0.63
    inson
    -0.62
    akeru
    -0.61
    åĽ
    -0.61
     striped
    -0.61
    POSITIVE LOGITS
     70
    2.65
     71
    1.93
     69
    1.93
    70
    1.82
     67
    1.79
     68
    1.77
     65
    1.69
     73
    1.66
     75
    1.63
     66
    1.56
    Activations Density 0.040%

    No Known Activations