© 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. 4-RES-JB
    11. 3676
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of movement or progression

    oai_token-act-pair · gpt-3.5-turbo

    the word "go" in various contexts

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

    No Comments

    Negative Logits
     accur
    -0.65
     ammon
    -0.62
     Aram
    -0.62
     inh
    -0.62
     accurately
    -0.61
     foll
    -0.59
     elbows
    -0.59
    creen
    -0.58
     densely
    -0.58
    race
    -0.58
    POSITIVE LOGITS
    vernment
    0.98
    verning
    0.95
    ardless
    0.89
    eker
    0.87
    ogly
    0.85
    eto
    0.84
    eff
    0.84
    ven
    0.83
    xit
    0.82
    ption
    0.81
    Activations Density 0.012%

    No Known Activations