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. 9-RES-JB
    6. 1150
    Prev
    Next
    INDEX
    Explanations

    actions of physical struggle or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of violent or aggressive actions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.99
    etheless
    -0.81
    ãĤ¦ãĤ¹
    -0.77
    fine
    -0.76
    vre
    -0.74
    enz
    -0.70
    TPP
    -0.70
    eah
    -0.69
    Higher
    -0.68
    conom
    -0.68
    POSITIVE LOGITS
     however
    1.19
     passers
    0.93
     she
    0.93
     though
    0.86
     they
    0.84
     Sergeant
    0.83
     he
    0.82
     Sgt
    0.80
     onlook
    0.76
     meanwhile
    0.74
    Activations Density 0.188%

    No Known Activations