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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9153
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of financial or economic transactions and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chnology
    -0.65
    emale
    -0.63
    nesday
    -0.61
    iterranean
    -0.58
     destro
    -0.58
    anwhile
    -0.57
     encount
    -0.57
    zona
    -0.57
    schild
    -0.57
     incent
    -0.56
    POSITIVE LOGITS
     his
    0.53
     affection
    0.52
     himself
    0.51
     Naruto
    0.50
    NRS
    0.50
     sarcastic
    0.49
     kisses
    0.48
     cuff
    0.47
     armour
    0.47
     betray
    0.46
    Activations Density 1.824%

    No Known Activations