© 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. 18491
    Prev
    Next
    INDEX
    Explanations

    references to a specific location named "Per"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "Per."

    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
    MpServer
    -0.71
    INESS
    -0.70
    aiden
    -0.68
     pneum
    -0.68
     Lazarus
    -0.67
    DERR
    -0.67
    ATIONAL
    -0.64
    naires
    -0.62
     dwar
    -0.62
    å¸
    -0.61
    POSITIVE LOGITS
    cussion
    1.36
    ceptions
    1.27
    ipher
    1.27
    uvian
    1.27
    secut
    1.27
    forming
    1.26
    malink
    1.26
    secution
    1.20
    ceived
    1.18
    imeter
    1.17
    Activations Density 0.021%

    No Known Activations