© 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. 10-RES-JB
    11. 18644
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing series or sequences of content

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing discussions or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©
    -0.75
    unts
    -0.73
    alias
    -0.69
    otrop
    -0.68
    effic
    -0.66
    ocally
    -0.66
    Ö¼
    -0.65
    soType
    -0.63
     valves
    -0.63
    objects
    -0.63
    POSITIVE LOGITS
     roundup
    1.36
     interview
    1.19
     podcast
    1.19
     installment
    1.14
     slideshow
    1.13
     infographic
    1.13
     quiz
    1.11
     recap
    1.09
     countdown
    1.08
     discussion
    1.08
    Activations Density 0.320%

    No Known Activations