© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3403
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions or states completing in the past

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence structure related to opinions or assessments

    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
     estranged
    -0.80
     Compass
    -0.74
     honored
    -0.73
     orchestr
    -0.72
     encomp
    -0.72
     fleeing
    -0.69
     travers
    -0.68
     purs
    -0.68
     eleph
    -0.67
     photograp
    -0.67
    POSITIVE LOGITS
    Posted
    1.45
    Reply
    1.41
    ________________
    1.37
    Anyway
    1.34
    Rated
    1.28
    Anonymous
    1.26
    Edited
    1.20
    anon
    1.20
    User
    1.19
    Guest
    1.12
    Activations Density 0.332%

    No Known Activations