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. 8-RES-JB
    6. 21852
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical movement or action towards specific destinations

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions involving searching and retrieving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Definitely
    -0.65
     Simply
    -0.64
    catentry
    -0.64
     Subtle
    -0.63
    £ı
    -0.63
    wikipedia
    -0.61
    etheless
    -0.61
     penchant
    -0.61
     stride
    -0.60
     Thumbnails
    -0.60
    POSITIVE LOGITS
    achu
    0.74
    BIL
    0.68
    oti
    0.68
    orate
    0.68
    uate
    0.66
    igate
    0.66
    ezvous
    0.66
     belongings
    0.64
     fathers
    0.64
    romptu
    0.63
    Activations Density 0.338%

    No Known Activations