© 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. 1-RES-JB
    11. 14221
    Prev
    Next
    INDEX
    Explanations

    references to specific subsets of items within a larger group

    oai_token-act-pair · gpt-3.5-turbo

    references to subgroups or collections within a larger category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sacrific
    -0.86
     horizont
    -0.78
    ayan
    -0.77
    endi
    -0.76
    lain
    -0.75
    onds
    -0.72
    maid
    -0.70
    ginx
    -0.69
    ongs
    -0.68
    ain
    -0.67
    POSITIVE LOGITS
     subset
    1.10
    TING
    0.76
    REDACTED
    0.74
    ="#
    0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.72
     guiActiveUn
    0.71
    actively
    0.70
    FIELD
    0.68
    population
    0.68
    typ
    0.68
    Activations Density 0.030%

    No Known Activations