© 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. 8-RES-JB
    11. 18451
    Prev
    Next
    INDEX
    Explanations

    specific mentions of names, places, and titles, especially focusing on individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific brand or company names

    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
    theless
    -0.74
    anwhile
    -0.69
     pleas
    -0.69
     stride
    -0.67
     altogether
    -0.67
     yourselves
    -0.65
     Petraeus
    -0.64
     wise
    -0.64
     root
    -0.62
     Warwick
    -0.61
    POSITIVE LOGITS
    ifles
    1.11
    eworks
    1.10
    istries
    1.08
    astery
    1.03
     Ltd
    0.98
    uctions
    0.97
    ifts
    0.95
    ework
    0.94
    ipel
    0.93
    itars
    0.92
    Activations Density 0.307%

    No Known Activations