© 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. 22644
    Prev
    Next
    INDEX
    Explanations

    actions or activities performed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs and their associated 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
    been
    -0.74
    cedented
    -0.70
    league
    -0.68
    arta
    -0.63
    veland
    -0.62
     Alley
    -0.60
    ibel
    -0.60
    enta
    -0.59
    eda
    -0.59
    thur
    -0.57
    POSITIVE LOGITS
     tremend
    0.82
    nesday
    0.68
    DEV
    0.63
     unsuccessfully
    0.62
     themselves
    0.59
    JV
    0.57
     him
    0.55
     brilliantly
    0.54
     unnecess
    0.54
    ãĤ¤ãĥĪ
    0.54
    Activations Density 0.653%

    No Known Activations