© 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. 6-RES-JB
    11. 17056
    Prev
    Next
    INDEX
    Explanations

    instances where the text contrasts different ideas or elements within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    contrasting ideas or points that begin with "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orc
    -0.73
    uay
    -0.73
    vet
    -0.70
    ory
    -0.70
    ven
    -0.69
    olars
    -0.69
    iltr
    -0.68
    vern
    -0.68
    oresc
    -0.67
    pot
    -0.67
    POSITIVE LOGITS
     also
    0.87
     actively
    0.74
     ALSO
    0.71
     downright
    0.71
     secondly
    0.70
    DES
    0.68
     possibly
    0.68
     insofar
    0.67
    Especially
    0.66
    Secondly
    0.63
    Activations Density 0.076%

    No Known Activations