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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10202
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact or influence of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the impact of policies or changes on various aspects of life

    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
    zar
    -0.76
    çĦ
    -0.73
    Tan
    -0.72
    TI
    -0.69
    BuyableInstoreAndOnline
    -0.68
    ç«
    -0.65
    SOURCE
    -0.65
    OVA
    -0.64
    beit
    -0.64
    éĸ
    -0.64
    POSITIVE LOGITS
     havoc
    1.06
     adversely
    0.92
    uate
    0.88
     impacts
    0.88
    ively
    0.87
    impact
    0.80
     interstate
    0.79
     impact
    0.78
     affecting
    0.77
     impacting
    0.76
    Activations Density 0.036%

    No Known Activations