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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6014
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating direction or position, vehicles, and ways of investigation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement or direction

    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
     justifies
    -0.64
    avier
    -0.63
     quot
    -0.62
     Compan
    -0.61
     ounce
    -0.61
    ":[
    -0.60
     intimid
    -0.60
     compromises
    -0.59
     interacts
    -0.58
    ifle
    -0.58
    POSITIVE LOGITS
     now
    0.84
    going
    0.82
    currently
    0.82
    joice
    0.79
     underway
    0.77
     ready
    0.73
    ready
    0.72
     NOW
    0.71
     primed
    0.69
     waiting
    0.69
    Activations Density 0.372%

    No Known Activations