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. 6-RES-JB
    6. 15847
    Prev
    Next
    INDEX
    Explanations

    action verbs combined with prepositions indicating a location or direction

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating action or activities that involve decision-making or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uum
    -0.77
     ][
    -0.67
    unity
    -0.67
    avin
    -0.65
    ortium
    -0.64
    blogspot
    -0.64
    cens
    -0.62
    elsius
    -0.61
    chev
    -0.60
    intention
    -0.60
    POSITIVE LOGITS
     alike
    1.00
     accordingly
    0.81
    instead
    0.74
     anew
    0.72
     prest
    0.69
     consequently
    0.69
    nob
    0.62
     ourselves
    0.62
     thereafter
    0.61
     whichever
    0.61
    Activations Density 0.359%

    No Known Activations