© 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. 0-RES-JB
    11. 8382
    Prev
    Next
    INDEX
    Explanations

    dates when users joined a certain website or platform

    oai_token-act-pair · gpt-3.5-turbo

    instances of user account join dates in profile information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corridors
    -0.77
     flow
    -0.76
     sellers
    -0.72
     distribution
    -0.71
     equivalent
    -0.71
     retail
    -0.68
     caution
    -0.68
     diversion
    -0.67
     regulation
    -0.66
     figures
    -0.65
    POSITIVE LOGITS
     Joined
    4.23
    Joined
    2.01
     Protoss
    1.26
     Ended
    1.18
     Flavoring
    1.17
     Posts
    1.15
     Blog
    1.13
    76561
    1.13
     Join
    1.12
    Merit
    1.10
    Activations Density 0.017%

    No Known Activations