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

    Neuronpedia

    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. 6-RES-JB
    11. 4387
    Prev
    Next
    INDEX
    Explanations

    references to manuscripts or written documents

    oai_token-act-pair · gpt-3.5-turbo

    references to manuscripts and related materials

    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
     Bore
    -0.73
    rx
    -0.73
    edin
    -0.69
    ered
    -0.65
    rador
    -0.65
    iggs
    -0.65
    Active
    -0.63
    bsite
    -0.63
    alty
    -0.63
    osta
    -0.63
    POSITIVE LOGITS
    uality
    0.73
    ãĤ£
    0.70
    chnology
    0.69
    ieri
    0.68
    989
    0.67
    tered
    0.65
     manuscripts
    0.65
    osa
    0.63
     nec
    0.62
    chin
    0.61
    Activations Density 0.049%

    No Known Activations