© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    keywords related to seeking advice, such as 'consult' or 'consultation'

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to seeking advice or professional guidance

    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
    bers
    -0.69
    boats
    -0.67
    multipl
    -0.66
     Janeiro
    -0.65
    bum
    -0.65
    buck
    -0.65
    gradation
    -0.64
    corn
    -0.62
     Bom
    -0.61
    XP
    -0.60
    POSITIVE LOGITS
     consulted
    0.87
    ancies
    0.80
     consult
    0.77
     Ples
    0.77
    ative
    0.75
    arial
    0.74
     advising
    0.72
     advise
    0.71
     Doctors
    0.69
     beforehand
    0.69
    Activations Density 0.043%

    No Known Activations