© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15361
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs describing physical actions

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the word "do" and variations of it, along with other short function words

    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
     Prometheus
    -0.73
    iHUD
    -0.65
     LCS
    -0.65
    DragonMagazine
    -0.64
     Ultron
    -0.62
    é¾
    -0.62
    ahime
    -0.62
     BaseType
    -0.62
     portions
    -0.61
     initiation
    -0.61
    POSITIVE LOGITS
    iqueness
    0.91
    uz
    0.77
    obin
    0.73
    arrass
    0.71
    heit
    0.69
    respected
    0.69
    beaut
    0.69
    uation
    0.68
    comfort
    0.68
    ogyn
    0.68
    Activations Density 0.391%

    No Known Activations