© 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. 7-RES-JB
    11. 11800
    Prev
    Next
    INDEX
    Explanations

    phrases related to fulfilling or not fulfilling promises

    oai_token-act-pair · gpt-3.5-turbo

    references to promises made, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -1.05
    entimes
    -0.81
    pmwiki
    -0.80
    atin
    -0.77
    mite
    -0.76
    arnaev
    -0.73
    ateur
    -0.72
    awk
    -0.72
    geant
    -0.71
    Oper
    -0.70
    POSITIVE LOGITS
     fulfilled
    1.03
     promise
    0.93
     promises
    0.91
    breaker
    0.82
    bringer
    0.81
    posts
    0.77
     pledges
    0.76
    fulness
    0.73
    holder
    0.72
     pledge
    0.71
    Activations Density 0.063%

    No Known Activations