Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15937
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or pacts

    oai_token-act-pair · gpt-3.5-turbo

    references to formal oaths and pledges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diff
    -0.67
     sticky
    -0.65
     addict
    -0.62
     bureaucratic
    -0.61
     Freud
    -0.61
     pleas
    -0.61
    çIJ
    -0.60
     fav
    -0.60
     Rudd
    -0.59
     purs
    -0.59
    POSITIVE LOGITS
     Oath
    3.51
    enium
    0.75
     Pact
    0.74
     GOODMAN
    0.73
     Ascend
    0.69
    ainer
    0.69
    maximum
    0.69
     Anthem
    0.68
    ieth
    0.68
    erity
    0.67
    Activations Density 0.011%

    No Known Activations