© 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. 17264
    Prev
    Next
    INDEX
    Explanations

    phrases related to the capabilities or functions of a device or product

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the capabilities or functions of objects or devices

    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
    rant
    -0.81
     Irving
    -0.75
     Lauder
    -0.66
     Closing
    -0.65
     Reasons
    -0.64
     Sunset
    -0.64
    raining
    -0.64
     hating
    -0.63
     Winner
    -0.63
     Brent
    -0.63
    POSITIVE LOGITS
    't
    1.31
    adian
    1.10
     withstand
    1.06
     optionally
    1.00
     penetrate
    0.98
     detect
    0.97
     utilize
    0.96
     handle
    0.95
    NOT
    0.94
     attach
    0.93
    Activations Density 0.168%

    No Known Activations