© 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. 2086
    Prev
    Next
    INDEX
    Explanations

    words or prefixes related to something negative or problematic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unsustainable practices or concepts

    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
    SHIP
    -0.72
    tsky
    -0.71
     Dynamics
    -0.70
     tanks
    -0.68
     Rams
    -0.68
     briefs
    -0.67
     Nanto
    -0.67
    phrine
    -0.67
     phases
    -0.65
     Guardians
    -0.64
    POSITIVE LOGITS
    aved
    1.18
    olicited
    1.17
    avour
    1.16
    killed
    1.11
    iders
    1.10
    atisf
    1.07
    ided
    1.05
    oci
    1.03
    ident
    1.02
    rep
    1.01
    Activations Density 0.015%

    No Known Activations