© 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. 22499
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the term "worth" and its variants in various 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
     deaf
    -0.69
     subtitle
    -0.64
     awoken
    -0.63
     cerebral
    -0.62
     heter
    -0.61
     Engineer
    -0.60
     Nou
    -0.59
     repressive
    -0.59
     cynical
    -0.59
     typo
    -0.58
    POSITIVE LOGITS
    worth
    1.53
    sburg
    1.13
    sworth
    0.99
    pole
    0.96
    iness
    0.87
    bye
    0.86
    emouth
    0.85
    ocity
    0.84
    sburgh
    0.84
    nton
    0.83
    Activations Density 0.006%

    No Known Activations