© 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. 2-RES-JB
    11. 1337
    Prev
    Next
    INDEX
    Explanations

    names of individuals (especially "Julia") within the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Julia" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holder
    -0.80
    ngth
    -0.79
    shirt
    -0.74
    creen
    -0.72
    company
    -0.72
    ciplinary
    -0.72
    andem
    -0.72
    dash
    -0.72
     boarding
    -0.71
    bike
    -0.70
    POSITIVE LOGITS
     Julia
    0.85
    udeau
    0.84
     Augusta
    0.78
    IRO
    0.77
     Sob
    0.76
     Schr
    0.75
    Ç
    0.75
     Andrews
    0.74
     CTR
    0.73
     Abram
    0.71
    Activations Density 0.015%

    No Known Activations