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

    Neuronpedia

    Jacobian LensNEW
    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. 21162
    Prev
    Next
    INDEX
    Explanations

    prepositions denoting location or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "In X" indicating context or explanation within a document

    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
     smack
    -0.72
     cherished
    -0.70
     deserved
    -0.69
    AFP
    -0.68
    papers
    -0.67
     homegrown
    -0.66
     linger
    -0.65
     Rodham
    -0.64
     Carney
    -0.64
     damned
    -0.64
    POSITIVE LOGITS
     addition
    1.01
    itialized
    0.97
    clusion
    0.94
    ventory
    0.94
    ception
    0.85
     Example
    0.83
    gest
    0.83
    juries
    0.82
    Each
    0.81
    clude
    0.81
    Activations Density 0.271%

    No Known Activations