© 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. 7802
    Prev
    Next
    INDEX
    Explanations

    job titles or professional roles

    oai_token-act-pair · gpt-3.5-turbo

    positions or titles related to leadership and organizational roles

    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
     notions
    -0.65
     assumptions
    -0.63
     conclusions
    -0.61
     strangers
    -0.61
     mug
    -0.61
     whim
    -0.60
     humidity
    -0.60
     fools
    -0.59
     myths
    -0.58
    ushes
    -0.58
    POSITIVE LOGITS
     overseeing
    1.03
     alongside
    0.82
    orney
    0.76
     Assist
    0.74
    ature
    0.69
    esses
    0.68
    piece
    0.67
     respectively
    0.67
     until
    0.67
     Leilan
    0.66
    Activations Density 0.279%

    No Known Activations