© 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 EvalsExportsinterp-engineNEWAPI 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. 9159
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or actions

    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
    ©¶æ¥µ
    -0.61
    ":"/
    -0.61
    ":["
    -0.60
    cy
    -0.59
    axis
    -0.59
    ãĤ§
    -0.59
    stro
    -0.57
    ensor
    -0.56
    },"
    -0.56
    onom
    -0.56
    POSITIVE LOGITS
     frequ
    0.75
     attended
    0.74
     resulted
    0.72
     ensued
    0.72
     overheard
    0.67
    livious
    0.66
     headlined
    0.66
     mistakenly
    0.65
    opened
    0.64
     chaired
    0.64
    Activations Density 0.795%

    No Known Activations