© 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. 3-RES-JB
    11. 3686
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral concepts and values

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions and opinions about justice or fairness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.70
     newcom
    -0.52
    çīĪ
    -0.50
    apter
    -0.49
    stellar
    -0.48
    SELECT
    -0.48
     Pwr
    -0.47
    MAP
    -0.47
    ODUCT
    -0.46
    ibaba
    -0.45
    POSITIVE LOGITS
     fuckin
    0.72
     fucking
    0.66
     goddamn
    0.62
     godd
    0.60
     stupid
    0.58
     whore
    0.57
     Trayvon
    0.55
     ain
    0.55
     Sharia
    0.55
     bigot
    0.54
    Activations Density 3.408%

    No Known Activations