© 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. 7-RES-JB
    11. 22934
    Prev
    Next
    INDEX
    Explanations

    phrases related to habitual tendencies or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe tendencies or behavioral patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gur
    -0.76
    yz
    -0.74
    arta
    -0.71
    lain
    -0.69
    ZA
    -0.64
    ania
    -0.62
    zbek
    -0.60
    fil
    -0.60
    ft
    -0.59
    KY
    -0.59
    POSITIVE LOGITS
    rils
    1.36
    entious
    1.18
    ril
    1.06
    erer
    0.88
    erers
    0.86
    erest
    0.84
     toward
    0.84
     towards
    0.80
    entimes
    0.80
    eman
    0.79
    Activations Density 0.018%

    No Known Activations