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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 14115
    Prev
    Next
    INDEX
    Explanations

    words related to advisory boards or positions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or references to statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plet
    -0.80
     dudes
    -0.73
     Rampage
    -0.72
     fandom
    -0.71
     suspic
    -0.70
     drunk
    -0.70
     Apocalypse
    -0.70
    xual
    -0.70
     punch
    -0.69
     worsh
    -0.69
    POSITIVE LOGITS
    Specifically
    1.14
    Therefore
    1.14
    Recommend
    1.09
    However
    1.07
    Acknowled
    1.07
    Currently
    1.06
    Companies
    1.05
    Additionally
    1.03
    Reporting
    1.02
    ###
    1.02
    Activations Density 0.686%

    No Known Activations