© 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. 9-RES-JB
    11. 15553
    Prev
    Next
    INDEX
    Explanations

    sentences instructing for certain actions or operations, often related to computer tasks or technology

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    farious
    -0.77
    zens
    -0.69
    eteenth
    -0.68
    aths
    -0.68
    ij士
    -0.66
    reb
    -0.65
    izens
    -0.65
    aws
    -0.65
    bia
    -0.64
    erity
    -0.64
    POSITIVE LOGITS
     ensures
    1.23
     allows
    1.18
     implies
    1.16
     corresponds
    1.15
     means
    1.13
     eliminates
    1.13
     assumes
    1.12
     applies
    1.11
     includes
    1.10
     prevents
    1.10
    Activations Density 0.184%

    No Known Activations