© 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. 10-RES-JB
    11. 12886
    Prev
    Next
    INDEX
    Explanations

    the name "Bo" with various numerical suffixes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Bo"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impunity
    -0.62
     conflicted
    -0.61
    Interstitial
    -0.60
     reuse
    -0.59
     CTR
    -0.58
     recess
    -0.58
     abiding
    -0.58
    Reloaded
    -0.58
     intent
    -0.57
     sworn
    -0.57
    POSITIVE LOGITS
    gey
    1.22
    iler
    1.13
    omer
    1.12
    ilers
    1.12
    ogie
    1.11
    oster
    1.09
    olean
    1.08
    omers
    1.07
    oby
    1.05
    onga
    1.05
    Activations Density 0.021%

    No Known Activations