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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 23853
    Prev
    Next
    INDEX
    Explanations

    words prefixed with "These" to indicate a group or collection of items

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating multiple instances or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pless
    -0.72
    iness
    -0.72
    ̶
    -0.71
    hood
    -0.70
    achus
    -0.67
    onement
    -0.67
    nah
    -0.67
    ë
    -0.67
    formance
    -0.66
    ning
    -0.65
    POSITIVE LOGITS
     fellows
    0.79
     findings
    0.76
     authors
    0.73
     kinds
    0.72
     results
    0.70
     newfound
    0.69
    eatures
    0.69
     contrasts
    0.68
     Situation
    0.67
     latter
    0.66
    Activations Density 0.062%

    No Known Activations