© 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. 9336
    Prev
    Next
    INDEX
    Explanations

    phrases indicating value or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "worth" or value

    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
     Hazel
    -0.68
     Sierra
    -0.68
     Jude
    -0.66
     Chamber
    -0.66
     Broad
    -0.65
     Dog
    -0.65
     Dogs
    -0.64
     Bus
    -0.64
     Frontier
    -0.63
     Cats
    -0.63
    POSITIVE LOGITS
     worth
    0.99
    iness
    0.97
    lihood
    0.91
    worth
    0.91
    ily
    0.84
    trade
    0.83
    daq
    0.83
    orth
    0.80
    ilege
    0.79
     worthwhile
    0.78
    Activations Density 0.011%

    No Known Activations