Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18823
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions followed by a continuation of the thought

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" in various contexts indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laun
    -0.70
    tained
    -0.70
    Synopsis
    -0.70
    hyde
    -0.66
    escription
    -0.66
    onte
    -0.65
    interstitial
    -0.65
     pione
    -0.63
    ursday
    -0.61
    lear
    -0.60
    POSITIVE LOGITS
     alas
    1.48
     fortunately
    1.21
     hey
    1.20
     luckily
    1.19
     anyways
    1.10
     thankfully
    1.06
     anyway
    1.06
     nonetheless
    1.05
     realistically
    1.03
     nevertheless
    1.01
    Activations Density 0.250%

    No Known Activations