© 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. 13117
    Prev
    Next
    INDEX
    Explanations

    detailed information or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of details and specifications

    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
    bang
    -0.72
     artificial
    -0.66
     programmed
    -0.65
     abstinence
    -0.63
     manned
    -0.63
     outdated
    -0.62
     toss
    -0.61
     pat
    -0.61
     misplaced
    -0.61
     amateur
    -0.61
    POSITIVE LOGITS
     Details
    3.00
    gro
    1.70
    Details
    1.53
    details
    1.24
     Specifications
    1.08
     masse
    0.99
     Options
    0.93
     Reviews
    0.90
     Detail
    0.86
    displayText
    0.80
    Activations Density 0.035%

    No Known Activations