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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6132
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific name "Ho."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ho" or variations of it within the text

    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
    Interstitial
    -0.75
    affer
    -0.73
    urgical
    -0.71
    SQL
    -0.70
     certs
    -0.69
     tabl
    -0.69
     rpm
    -0.69
    acus
    -0.68
     delim
    -0.66
    ropolitan
    -0.65
    POSITIVE LOGITS
     Ho
    3.70
    Ho
    2.77
     ho
    1.80
    ho
    1.76
     HO
    1.72
     Hoo
    1.43
     Lo
    1.28
     Hop
    1.25
     Wo
    1.18
     Hof
    1.17
    Activations Density 0.016%

    No Known Activations