© 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. 10-RES-JB
    11. 2667
    Prev
    Next
    INDEX
    Explanations

    words related to technology and software development, focusing on terms related to "R&D" and related technological activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter 'R' followed by numbers, indicating references to various R&B music groups or related content

    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
     cart
    -0.76
     âĵĺ
    -0.73
     hers
    -0.66
     greens
    -0.65
     mine
    -0.65
     yours
    -0.64
     pear
    -0.64
     thor
    -0.63
     minimized
    -0.62
     retina
    -0.62
    POSITIVE LOGITS
    outine
    1.39
    otation
    1.38
    ounding
    1.30
    ansom
    1.30
    otten
    1.30
    haps
    1.28
    ipples
    1.24
    ivalry
    1.23
    ifles
    1.22
    ascal
    1.20
    Activations Density 0.040%

    No Known Activations