© 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. 6-RES-JB
    11. 11632
    Prev
    Next
    INDEX
    Explanations

    phrases related to change or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to changing or improving a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.79
    chem
    -0.68
     tatt
    -0.64
    enegger
    -0.63
    hip
    -0.63
    ged
    -0.61
     laid
    -0.61
    iston
    -0.61
    hetical
    -0.61
    nih
    -0.59
    POSITIVE LOGITS
    wagen
    0.84
    ichick
    0.76
    itect
    0.75
    ruciating
    0.74
    allery
    0.73
    ernaut
    0.72
    erous
    0.69
    gressive
    0.66
    rocal
    0.65
    pter
    0.65
    Activations Density 0.017%

    No Known Activations