© 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. 8-RES-JB
    11. 3277
    Prev
    Next
    INDEX
    Explanations

    phrases inviting interaction or engagement with content

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "feel free" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.71
     Camer
    -0.70
     Shutterstock
    -0.67
     Mub
    -0.67
     Bastard
    -0.65
     notch
    -0.65
     Shut
    -0.62
     misc
    -0.59
     Parenthood
    -0.58
     externalToEVAOnly
    -0.58
    POSITIVE LOGITS
    INGS
    0.91
    rils
    0.82
     comfortable
    0.82
    ulz
    0.80
    ings
    0.80
     compelled
    0.78
    istas
    0.78
    Pad
    0.74
     sensations
    0.73
    phasis
    0.73
    Activations Density 0.039%

    No Known Activations