© 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. 11-RES-JB
    11. 7690
    Prev
    Next
    INDEX
    Explanations

    links or actions related to sharing content

    oai_token-act-pair · gpt-3.5-turbo

    references to actions related to opening or publishing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hem
    -0.76
    hots
    -0.71
    hers
    -0.69
    hens
    -0.68
    hern
    -0.68
    amy
    -0.67
    auts
    -0.66
    heet
    -0.65
    amera
    -0.65
    oming
    -0.64
    POSITIVE LOGITS
    ¨
    0.60
    §
    0.59
     sentence
    0.54
     understatement
    0.51
    ¢
    0.51
     Putting
    0.50
     injection
    0.48
    ŀ
    0.48
    Posted
    0.47
    DI
    0.47
    Activations Density 0.095%

    No Known Activations