© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    generic statements followed by numerical values

    oai_token-act-pair · gpt-3.5-turbo

    statements that refer to the existence of entities or concepts

    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
     proportions
    -0.64
    buster
    -0.57
     bag
    -0.55
     Handbook
    -0.53
     mindset
    -0.53
     Habit
    -0.52
    hood
    -0.52
     alias
    -0.52
    wake
    -0.52
     Appearance
    -0.52
    POSITIVE LOGITS
     plenty
    0.87
    aido
    0.86
    女
    0.83
    etsk
    0.75
     occasions
    0.74
    nces
    0.73
     exceptions
    0.69
    akia
    0.68
    ibaba
    0.67
    umerable
    0.67
    Activations Density 0.409%

    No Known Activations