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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 1088
    Prev
    Next
    INDEX
    Explanations

    phrases related to making mistakes and receiving feedback

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant effort or achievements

    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
    soDeliveryDate
    -0.75
    hub
    -0.72
    sonian
    -0.64
     Compass
    -0.61
    currently
    -0.59
    intendent
    -0.56
     TBD
    -0.55
    oglu
    -0.54
     Currently
    -0.53
    jam
    -0.53
    POSITIVE LOGITS
     himself
    1.30
     Himself
    0.96
     herself
    0.79
     his
    0.75
     personality
    0.73
     persona
    0.73
     charisma
    0.73
     raping
    0.68
     demeanor
    0.68
     remorse
    0.67
    Activations Density 1.058%

    No Known Activations