© 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. 7053
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons or contrasts within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "when it comes to."

    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
    ©¶æ¥µ
    -0.85
    Written
    -0.74
     âĶľ
    -0.73
    CBC
    -0.69
    ;;;;;;;;
    -0.67
    ais
    -0.65
    Released
    -0.65
    akin
    -0.65
    º
    -0.64
     Patel
    -0.64
    POSITIVE LOGITS
     regards
    0.96
     matters
    0.82
     finances
    0.81
     regard
    0.80
     selecting
    0.76
     determining
    0.76
     resolving
    0.76
     shaping
    0.76
     respecting
    0.75
     diagn
    0.73
    Activations Density 0.046%

    No Known Activations