© 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. 9-RES-JB
    11. 9936
    Prev
    Next
    INDEX
    Explanations

    phrases indicating occasional or intermittent actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to frequency and recurrence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Xer
    -0.55
     tob
    -0.54
     NI
    -0.53
    osate
    -0.53
     certific
    -0.52
    ryu
    -0.52
     rigged
    -0.52
     swaps
    -0.50
    adeon
    -0.50
     lobbyists
    -0.49
    POSITIVE LOGITS
    minute
    0.75
    chance
    0.75
    estone
    0.71
    ĩ
    0.69
    ãĥŁ
    0.67
    Else
    0.66
    ace
    0.64
     imaginable
    0.64
    cture
    0.63
    thens
    0.63
    Activations Density 0.065%

    No Known Activations