© 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. 2-RES-JB
    11. 9189
    Prev
    Next
    INDEX
    Explanations

    the word "oft" (often) used in texts

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "oft" and variations thereof, indicating a focus on frequent occurrences or themes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Syndicate
    -0.80
    osponsors
    -0.75
     Enhancement
    -0.71
     Handling
    -0.71
    士
    -0.70
     Federation
    -0.70
     Compatibility
    -0.68
     Universities
    -0.68
     Murdoch
    -0.68
     Membership
    -0.67
    POSITIVE LOGITS
    entimes
    1.65
    ventory
    0.91
    wered
    0.81
    cil
    0.80
    fort
    0.80
    felt
    0.79
    anc
    0.78
    ache
    0.76
    jo
    0.75
    stant
    0.75
    Activations Density 0.017%

    No Known Activations