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. 1-RES-JB
    6. 12783
    Prev
    Next
    INDEX
    Explanations

    phrases related to removal or separation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of "getting away" or escaping from something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.77
    ammy
    -0.76
    xual
    -0.73
    ums
    -0.73
    enegger
    -0.71
    igel
    -0.71
    ionic
    -0.71
    oly
    -0.69
    obal
    -0.69
     Zeit
    -0.67
    POSITIVE LOGITS
     away
    0.92
    lehem
    0.80
     Away
    0.80
    à©
    0.75
    away
    0.74
     waivers
    0.71
    Ĭ±
    0.70
    atcher
    0.70
    ADRA
    0.69
    ALSE
    0.67
    Activations Density 0.027%

    No Known Activations