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. 6-RES-JB
    6. 23647
    Prev
    Next
    INDEX
    Explanations

    phrases related to the lifting of restrictions or bans

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of lifting, elevating, or removing restrictions and barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errilla
    -0.77
    lished
    -0.70
    present
    -0.66
    Future
    -0.65
    ãĥ£
    -0.64
    printf
    -0.63
    perture
    -0.62
    TAG
    -0.62
    915
    -0.62
    Cola
    -0.62
    POSITIVE LOGITS
     weights
    1.07
     lift
    1.02
     lifting
    0.99
     lifted
    0.96
     lifts
    0.88
    lift
    0.80
    hens
    0.79
     tremend
    0.78
    hetically
    0.77
    weight
    0.77
    Activations Density 0.024%

    No Known Activations