© 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. 21389
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tools commonly used in technology, such as the term "right-click"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rights or entitlements

    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
     Plum
    -0.68
    nels
    -0.64
    hran
    -0.63
     Flavoring
    -0.63
    anut
    -0.63
    DragonMagazine
    -0.63
    nown
    -0.62
    exempt
    -0.61
    patch
    -0.61
    allo
    -0.61
    POSITIVE LOGITS
     citizenship
    0.65
    hander
    0.65
    Ô
    0.64
     Wrong
    0.60
     axis
    0.60
    ovych
    0.60
    ACTED
    0.59
     populism
    0.59
     inherit
    0.59
     emancipation
    0.58
    Activations Density 0.147%

    No Known Activations