© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24010
    Prev
    Next
    INDEX
    Explanations

    proper nouns containing the word 'worth'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "worth" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nou
    -0.64
     awoken
    -0.63
     polar
    -0.63
     subtitle
    -0.63
     Bad
    -0.62
     lull
    -0.62
     other
    -0.61
     cerebral
    -0.61
     Chronic
    -0.59
     scratch
    -0.57
    POSITIVE LOGITS
    worth
    1.78
    sburg
    1.09
    sworth
    1.08
    emouth
    0.94
    fman
    0.93
    INGTON
    0.92
    \\\\\\\\
    0.90
    nance
    0.88
    owa
    0.87
    lett
    0.87
    Activations Density 0.008%

    No Known Activations