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. 10-RES-JB
    6. 2148
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speculation or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    statements making suggestions or indicating possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.78
    arak
    -0.76
    à¦
    -0.76
    apest
    -0.74
    arez
    -0.68
    ocaust
    -0.67
    ãĤ´ãĥ³
    -0.67
    utch
    -0.65
    reth
    -0.65
    aughed
    -0.65
    POSITIVE LOGITS
     whoever
    0.98
     perhaps
    0.91
     there
    0.86
     they
    0.85
     tensions
    0.84
     something
    0.84
     maybe
    0.83
     someone
    0.81
     these
    0.79
     somebody
    0.78
    Activations Density 0.237%

    No Known Activations