© 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. 7-RES-JB
    11. 16759
    Prev
    Next
    INDEX
    Explanations

    references to various texts or literary works across different cultures and themes

    oai_token-act-pair · gpt-3.5-turbo

    references to various historical and religious texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peas
    -0.75
    ittens
    -0.71
    VC
    -0.71
     Canary
    -0.69
    uppet
    -0.68
    cffff
    -0.67
     Mane
    -0.66
    ratulations
    -0.65
     twitch
    -0.65
     Derby
    -0.63
    POSITIVE LOGITS
     manuscripts
    1.09
     manuscript
    1.06
     texts
    1.04
    books
    0.98
     textual
    0.98
     translated
    0.95
    ographers
    0.92
     aloud
    0.92
     Interpret
    0.90
     scriptures
    0.89
    Activations Density 0.129%

    No Known Activations