© 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. 10-RES-JB
    11. 10092
    Prev
    Next
    INDEX
    Explanations

    words related to something being untrustworthy or unreliable

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trust issues or untrustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gorilla
    -0.74
    hyde
    -0.67
    anwhile
    -0.64
    姫
    -0.64
    SHIP
    -0.62
    Reviewer
    -0.62
     Mercury
    -0.62
     vans
    -0.60
     coefficient
    -0.60
     stages
    -0.60
    POSITIVE LOGITS
    itled
    1.43
    rained
    1.42
    rans
    1.39
    apped
    1.31
    ested
    1.30
    rust
    1.26
    ruly
    1.25
    arget
    1.24
    race
    1.23
    oward
    1.23
    Activations Density 0.018%

    No Known Activations