© 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. 2-RES-JB
    11. 12659
    Prev
    Next
    INDEX
    Explanations

    references to credibility, including words related to trustworthiness and reliability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to credibility and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meal
    -0.75
     Boat
    -0.72
     Nurs
    -0.71
     Parenthood
    -0.69
    hap
    -0.68
     Klu
    -0.65
    Ò
    -0.63
     Abandon
    -0.63
    Pause
    -0.63
    akings
    -0.63
    POSITIVE LOGITS
    ibly
    1.25
    ulously
    1.20
    enza
    1.20
     cred
    1.11
    ulous
    1.11
    iosity
    0.92
    ibles
    0.91
    ibility
    0.89
    entials
    0.88
    icator
    0.87
    Activations Density 0.009%

    No Known Activations