© 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. 1-RES-JB
    11. 9477
    Prev
    Next
    INDEX
    Explanations

    measurements of length expressed in feet

    oai_token-act-pair · gpt-3.5-turbo

    measurements of height, particularly in feet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptives
    -0.77
     Mothers
    -0.74
    ulator
    -0.71
     Turing
    -0.71
    esan
    -0.66
    amus
    -0.66
     Strange
    -0.64
    stakes
    -0.64
    66666666
    -0.64
    lyak
    -0.63
    POSITIVE LOGITS
     ft
    1.08
    entimes
    0.86
    airs
    0.81
    rib
    0.79
     rapp
    0.79
     Ft
    0.79
     fri
    0.78
    veland
    0.76
    rench
    0.76
     refuel
    0.75
    Activations Density 0.005%

    No Known Activations