© 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. 3-RES-JB
    11. 5693
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "old" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "old"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mathemat
    -0.81
    Ĥİ
    -0.79
     ILCS
    -0.79
     exha
    -0.78
    pload
    -0.74
     cumbers
    -0.74
    otos
    -0.73
     sclerosis
    -0.71
     "$:/
    -0.71
     teasp
    -0.71
    POSITIVE LOGITS
    est
    1.00
    rums
    0.99
    face
    0.84
    stones
    0.82
     fashioned
    0.80
    esc
    0.76
     Trafford
    0.75
    bury
    0.75
    ster
    0.75
    sworth
    0.74
    Activations Density 0.022%

    No Known Activations