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

    Neuronpedia

    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. 8970
    Prev
    Next
    INDEX
    Explanations

    words related to looking for something or attempting to achieve a goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a desire or intent to take action

    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
    shown
    -0.74
    workers
    -0.73
    worth
    -0.71
    eros
    -0.70
    bending
    -0.68
    mask
    -0.68
    roy
    -0.67
     commanded
    -0.65
    mone
    -0.64
     sake
    -0.61
    POSITIVE LOGITS
     emulate
    1.08
     capitalize
    0.92
     engage
    0.89
     revive
    0.88
     improve
    0.87
     incorporate
    0.86
     expand
    0.86
     broaden
    0.85
     avoid
    0.82
     strengthen
    0.82
    Activations Density 0.064%

    No Known Activations