© 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. 9476
    Prev
    Next
    INDEX
    Explanations

    descriptions related to performance or execution of tasks

    oai_token-act-pair · gpt-3.5-turbo

    instances of detailed descriptions or actions

    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
    edom
    -0.74
    ĸļ
    -0.69
    ctica
    -0.67
    ciation
    -0.63
    afety
    -0.61
     Ri
    -0.59
    ngth
    -0.58
     Adin
    -0.58
    yrights
    -0.58
    phabet
    -0.55
    POSITIVE LOGITS
    DragonMagazine
    0.73
    EStream
    0.64
    Introduced
    0.58
    Psy
    0.56
    Urban
    0.55
    Spect
    0.53
    uls
    0.52
    Frag
    0.51
    CLASS
    0.51
    Gallery
    0.50
    Activations Density 0.211%

    No Known Activations