© 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. 2-RES-JB
    11. 4198
    Prev
    Next
    INDEX
    Explanations

    references to newly introduced or latest things

    oai_token-act-pair · gpt-3.5-turbo

    references to new or recent items and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urer
    -0.83
     Handling
    -0.73
    ochet
    -0.71
    omical
    -0.71
    arching
    -0.67
    omy
    -0.66
    alties
    -0.65
    phasis
    -0.65
    RF
    -0.64
    conom
    -0.63
    POSITIVE LOGITS
     additions
    1.03
     developments
    0.91
     arrivals
    0.81
    bies
    0.79
     edition
    0.78
    foundland
    0.76
     incarnation
    0.76
     revision
    0.74
     generation
    0.73
     newest
    0.73
    Activations Density 0.007%

    No Known Activations