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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 24455
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or progression in a specific direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direction or movement towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cu
    -0.95
    drivers
    -0.75
    glers
    -0.74
     Cosponsors
    -0.73
    eyes
    -0.73
    ounce
    -0.73
    chin
    -0.72
    RIP
    -0.72
    zai
    -0.71
    deal
    -0.68
    POSITIVE LOGITS
    wards
    1.00
     adulthood
    0.95
     achieving
    0.92
     extinction
    0.88
     infinity
    0.87
    WARD
    0.83
     solving
    0.82
     resolving
    0.81
     completing
    0.81
     goal
    0.80
    Activations Density 0.050%

    No Known Activations