© 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. 21225
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to specific topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a continuation or elaboration of a topic

    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
    atars
    -0.88
    elligent
    -0.63
    osponsors
    -0.63
    bart
    -0.63
    ¬¼
    -0.61
    entimes
    -0.61
     stake
    -0.61
    apult
    -0.61
    nai
    -0.60
    ãģł
    -0.60
    POSITIVE LOGITS
     yeah
    0.80
     parity
    0.77
     yes
    0.77
     namely
    0.74
     meanwhile
    0.72
     interestingly
    0.67
    76561
    0.65
    yeah
    0.62
    well
    0.61
    ccording
    0.61
    Activations Density 0.249%

    No Known Activations