© 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. 242
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe the intensity or scale of a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing exaggeration or hyperbole

    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
    ellar
    -0.72
    RN
    -0.71
    IBLE
    -0.65
    URR
    -0.65
    /#
    -0.64
    ITED
    -0.64
    zilla
    -0.59
    cellent
    -0.57
    Route
    -0.56
    Mur
    -0.56
    POSITIVE LOGITS
    ontent
    0.81
     dispos
    0.67
    thren
    0.64
    than
    0.64
    heit
    0.64
    ados
    0.61
     Remain
    0.59
    upon
    0.58
    comings
    0.57
     Kern
    0.57
    Activations Density 0.316%

    No Known Activations