© 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. 23517
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a preference for one option over another

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "rather."

    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
    DD
    -0.71
    PU
    -0.65
    raz
    -0.64
     MIL
    -0.63
    STER
    -0.62
    ENE
    -0.61
    ORN
    -0.60
    amba
    -0.60
     championship
    -0.60
    opal
    -0.59
    POSITIVE LOGITS
    tons
    0.88
     than
    0.79
    than
    0.75
     Than
    0.75
     ado
    0.75
    swer
    0.72
    bilt
    0.71
     Rather
    0.68
     interestingly
    0.68
    quickShipAvailable
    0.67
    Activations Density 0.010%

    No Known Activations