© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1927
    Prev
    Next
    INDEX
    Explanations

    specific patterns of text structures starting with "of the" followed by different terms such as "deceased," "pistol," or "source."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" 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
    ypes
    -0.76
    ype
    -0.76
    vl
    -0.72
    fulness
    -0.71
    flow
    -0.70
    agy
    -0.70
    pour
    -0.67
    =""
    -0.66
    flows
    -0.66
    ventions
    -0.65
    POSITIVE LOGITS
     respective
    1.25
     deceased
    0.99
     nearest
    0.92
     chosen
    0.90
     aforementioned
    0.90
     offending
    0.88
     upcoming
    0.86
     preceding
    0.84
     corporation
    0.81
     defunct
    0.80
    Activations Density 0.347%

    No Known Activations