© 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. 6-RES-JB
    11. 17658
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity named "Merc" with different variations of numbers attached to it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Merc" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lay
    -0.79
    doors
    -0.78
    åĤ
    -0.76
    FORMATION
    -0.76
     Kimmel
    -0.73
     Ancients
    -0.72
    gger
    -0.71
    brate
    -0.71
     Frie
    -0.71
    study
    -0.70
    POSITIVE LOGITS
    ifully
    1.21
    iless
    1.16
    enaries
    1.12
    iful
    1.04
    uria
    0.89
    ues
    0.83
    iously
    0.81
    urious
    0.81
    adian
    0.80
    aine
    0.80
    Activations Density 0.020%

    No Known Activations