© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 12773
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing verbs conveying intent or goals

    oai_token-act-pair · gpt-3.5-turbo

    the word "aims" or phrases indicating intention or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anymore
    -0.68
    omer
    -0.61
    $$
    -0.59
    Todd
    -0.55
    lot
    -0.55
     duplicate
    -0.54
     properly
    -0.54
     Slip
    -0.53
    FORMATION
    -0.53
     Nate
    -0.53
    POSITIVE LOGITS
     aims
    3.46
     aim
    2.17
     strives
    1.69
     hopes
    1.62
     focuses
    1.58
     goals
    1.58
     objectives
    1.57
     intends
    1.57
     seeks
    1.54
     aiming
    1.54
    Activations Density 0.016%

    No Known Activations