© 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. 3-RES-JB
    11. 14763
    Prev
    Next
    INDEX
    Explanations

    names or titles with 'Sr' as a suffix

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with a name, particularly "Sr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.72
    Front
    -0.72
     whistle
    -0.71
    toggle
    -0.69
    watching
    -0.68
    */(
    -0.67
     Zucker
    -0.66
     WikiLeaks
    -0.66
    eals
    -0.66
     Petraeus
    -0.64
    POSITIVE LOGITS
     Sr
    1.04
    uti
    0.95
    ansky
    0.87
    itta
    0.84
    ategy
    0.84
    uth
    0.82
    abba
    0.81
    hes
    0.80
    hesis
    0.79
    angler
    0.78
    Activations Density 0.007%

    No Known Activations