© 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. 22550
    Prev
    Next
    INDEX
    Explanations

    names related to a specific person, "Daly"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names

    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
    acter
    -0.69
    roup
    -0.69
    rial
    -0.68
     grop
    -0.65
    mus
    -0.62
    ãģĨ
    -0.62
    pal
    -0.62
    ilion
    -0.62
     Templ
    -0.62
    hun
    -0.61
    POSITIVE LOGITS
     Daly
    1.89
     Dak
    1.77
     Dart
    1.65
     Dob
    1.64
     Dawson
    1.61
     DH
    1.58
     Dixon
    1.56
     DI
    1.55
     Dum
    1.54
     Daw
    1.52
    Activations Density 0.077%

    No Known Activations