© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13982
    Prev
    Next
    INDEX
    Explanations

    numerals followed by words related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consistency and stability in various contexts

    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
     ambitions
    -0.61
     prophetic
    -0.58
     astronomers
    -0.56
     Yuri
    -0.55
    ogun
    -0.55
    ndra
    -0.54
     Dreams
    -0.52
     Religion
    -0.52
     Syndrome
    -0.51
     fortune
    -0.51
    POSITIVE LOGITS
     concess
    0.82
     specified
    0.75
     regulated
    0.72
    ļéĨĴ
    0.71
     prescribed
    0.70
     cheapest
    0.69
     tariff
    0.68
     expense
    0.67
    specified
    0.65
     increments
    0.64
    Activations Density 0.995%

    No Known Activations