© 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. 20055
    Prev
    Next
    INDEX
    Explanations

    names matching 'Vasquez'

    oai_token-act-pair · gpt-3.5-turbo

    the name "Vasquez" and its variations

    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
     er
    -0.64
     TOM
    -0.64
     alternative
    -0.62
     SN
    -0.62
     Sound
    -0.61
     autumn
    -0.61
     standard
    -0.60
     Id
    -0.60
     only
    -0.60
     Adventure
    -0.59
    POSITIVE LOGITS
    quez
    4.88
    ques
    1.57
    ierrez
    1.31
    ibaba
    1.20
    cedes
    1.20
    anchez
    1.16
    irez
    1.15
    arez
    1.11
    zona
    1.08
    iewicz
    1.06
    Activations Density 0.023%

    No Known Activations