© 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. 2-RES-JB
    11. 14431
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names associated with confrontation and negative sentiment

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly those associated with legal or investigative contexts

    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
     lacking
    -0.75
    catentry
    -0.71
     Berm
    -0.69
    è¦ļéĨĴ
    -0.67
     PLUS
    -0.64
     Dare
    -0.61
    é¾įå
    -0.59
     somew
    -0.59
     wealthy
    -0.58
     Maced
    -0.58
    POSITIVE LOGITS
    schild
    0.86
    inki
    0.85
    tty
    0.84
    puff
    0.81
    idan
    0.80
    anka
    0.77
    lain
    0.77
    ibaba
    0.77
    ikh
    0.76
    ogi
    0.76
    Activations Density 0.146%

    No Known Activations