© 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. 4258
    Prev
    Next
    INDEX
    Explanations

    words related to specific actions or objects around which news or media stories are structured

    oai_token-act-pair · gpt-3.5-turbo

    terms related to media and societal issues

    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
    Magikarp
    -0.65
    addin
    -0.61
    soDeliveryDate
    -0.61
    »Ĵ
    -0.60
    çĶ°
    -0.58
    Interstitial
    -0.56
    ractical
    -0.55
    ilingual
    -0.53
    assadors
    -0.53
    ilant
    -0.52
    POSITIVE LOGITS
     altogether
    0.87
     reins
    0.65
     entirely
    0.59
     prematurely
    0.58
     onto
    0.54
     reservation
    0.54
     anymore
    0.54
    til
    0.53
     deposit
    0.53
     ASAP
    0.53
    Activations Density 0.893%

    No Known Activations