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. 8-RES-JB
    6. 17992
    Prev
    Next
    INDEX
    Explanations

    information related to government policies and financial measures

    oai_token-act-pair · gpt-3.5-turbo

    language related to financial and economic obligations or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colored
    -0.91
     Theater
    -0.91
     honor
    -0.90
     honors
    -0.86
     Bundy
    -0.85
     Jr
    -0.81
     badass
    -0.81
     uh
    -0.80
    Chuck
    -0.79
     neocons
    -0.79
    POSITIVE LOGITS
     licences
    1.47
     NHS
    1.44
     programmes
    1.40
     programme
    1.36
     £
    1.36
     organisations
    1.34
     counselling
    1.30
     licence
    1.29
     behavioural
    1.28
     modelling
    1.25
    Activations Density 1.389%

    No Known Activations