© 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. 0-RES-JB
    11. 5104
    Prev
    Next
    INDEX
    Explanations

    occurrences related to a particular term "HA"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "HA" within text segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     margins
    -0.73
     nic
    -0.69
     contr
    -0.66
     bounds
    -0.65
     quarters
    -0.64
     lines
    -0.63
     calib
    -0.63
     domin
    -0.61
     origins
    -0.60
     empty
    -0.60
    POSITIVE LOGITS
    HA
    4.24
    HE
    1.71
    HAHA
    1.59
    ha
    1.53
    HS
    1.53
    HT
    1.52
     HA
    1.49
    HI
    1.48
    CHA
    1.47
    HAHAHAHA
    1.43
    Activations Density 0.016%

    No Known Activations