© 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. 4-RES-JB
    11. 7020
    Prev
    Next
    INDEX
    Explanations

    references to the word "Dam" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or brand related to a notable subject

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

    No Comments

    Negative Logits
     Hawaiian
    -0.72
    avorite
    -0.72
     Subtle
    -0.66
     Garner
    -0.64
     syrup
    -0.64
     profiling
    -0.63
    holders
    -0.62
     clipboard
    -0.62
     needle
    -0.61
     sugars
    -0.60
    POSITIVE LOGITS
    ukong
    1.16
    ascus
    0.99
    ned
    0.93
    nation
    0.90
    vid
    0.88
    iour
    0.86
    iani
    0.86
    mit
    0.83
    abil
    0.82
    ifer
    0.80
    Activations Density 0.009%

    No Known Activations