Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3219
    Prev
    Next
    INDEX
    Explanations

    actions involving physical contact or movement between individuals

    oai_token-act-pair · gpt-3.5-turbo

    connections and interactions between individuals, particularly emphasizing relationships and group dynamics

    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
    quartered
    -0.63
    htaking
    -0.57
    cdn
    -0.56
    cair
    -0.55
     guiName
    -0.54
     depends
    -0.53
    pires
    -0.53
    enna
    -0.53
     Neighbor
    -0.52
    osponsors
    -0.51
    POSITIVE LOGITS
     humiliating
    0.57
     himself
    0.54
     incrim
    0.54
     unsuspecting
    0.53
     repentance
    0.53
     confession
    0.52
     humiliation
    0.51
     afterwards
    0.50
     pen
    0.50
    Fax
    0.49
    Activations Density 1.894%

    No Known Activations