© 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. 4-RES-JB
    11. 6945
    Prev
    Next
    INDEX
    Explanations

    proper names 'Tim' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tim."

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

    No Comments

    Negative Logits
    Magikarp
    -0.79
    cffff
    -0.70
    Reloaded
    -0.68
    avorite
    -0.68
    Untitled
    -0.65
     SCHOOL
    -0.63
     poaching
    -0.63
    KI
    -0.63
     NETWORK
    -0.62
    RAFT
    -0.62
    POSITIVE LOGITS
    estamp
    1.35
    othy
    1.12
    mons
    1.04
    eless
    1.00
     Ferr
    0.97
    bre
    0.97
    mins
    0.91
    my
    0.88
    elines
    0.87
    oleon
    0.86
    Activations Density 0.009%

    No Known Activations