© 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. 0-RES-JB
    11. 16511
    Prev
    Next
    INDEX
    Explanations

    words related to aiming or targeting

    oai_token-act-pair · gpt-3.5-turbo
    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
     card
    -0.73
     slip
    -0.68
     flap
    -0.67
     session
    -0.63
     column
    -0.62
     redu
    -0.62
     polymer
    -0.61
     encounter
    -0.60
     random
    -0.59
     Tea
    -0.59
    POSITIVE LOGITS
    aim
    4.52
    Aim
    1.33
     Aim
    1.29
    aimon
    1.26
    aiman
    1.12
    amation
    1.05
    ai
    1.02
    air
    0.93
    uel
    0.92
    amera
    0.91
    Activations Density 0.010%

    No Known Activations