© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3077
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs indicating thinking or considering

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express contemplation or consideration of ideas

    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
    ARDS
    -0.71
    ALL
    -0.69
     Hide
    -0.67
     Kats
    -0.61
    ORPG
    -0.60
    Bron
    -0.59
    SPONSORED
    -0.59
     toe
    -0.58
     flats
    -0.58
    anty
    -0.58
    POSITIVE LOGITS
    fulness
    1.31
    lessly
    1.16
    fully
    1.02
    lessness
    0.99
    orial
    0.92
     provoking
    0.91
     aloud
    0.83
    less
    0.82
    pad
    0.81
    ileaks
    0.80
    Activations Density 0.024%

    No Known Activations