© 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. 21527
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and website development

    oai_token-act-pair · gpt-3.5-turbo

    instances of individual words or tokens with low frequency

    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
     Metall
    -0.80
     Schwar
    -0.72
     Stones
    -0.68
     Rolls
    -0.68
     Canaver
    -0.68
     Kit
    -0.66
     Thrones
    -0.66
     Allied
    -0.66
     Pack
    -0.65
     Isle
    -0.65
    POSITIVE LOGITS
    terday
    1.15
    anwhile
    1.10
    theless
    1.04
    etheless
    0.99
    maxwell
    0.99
    ividual
    0.87
    ogether
    0.83
    ilogy
    0.82
    redients
    0.82
    rontal
    0.82
    Activations Density 0.128%

    No Known Activations