© 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. 7-RES-JB
    11. 1794
    Prev
    Next
    INDEX
    Explanations

    instances of altruistic actions or helpful behaviors

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to assistance and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.89
    Available
    -0.81
    Stretch
    -0.77
    idan
    -0.76
    appropriately
    -0.75
     Said
    -0.71
    Rem
    -0.70
    Especially
    -0.70
    Get
    -0.70
    shed
    -0.69
    POSITIVE LOGITS
     bike
    0.88
     commerce
    0.83
     physic
    0.83
     bicycle
    0.79
     automobile
    0.79
     money
    0.79
     automobiles
    0.76
     human
    0.75
     transportation
    0.75
     person
    0.75
    Activations Density 0.577%

    No Known Activations