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. 10443
    Prev
    Next
    INDEX
    Explanations

    phrases related to raising awareness about various topics or causes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to awareness, support, safety, and order in the context of societal issues

    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
     slit
    -0.59
     fing
    -0.59
     master
    -0.56
     landlord
    -0.55
     inventor
    -0.55
     singular
    -0.55
     fucked
    -0.55
     boxed
    -0.54
     parted
    -0.53
    akespe
    -0.53
    POSITIVE LOGITS
     morale
    0.74
    flows
    0.71
    icial
    0.70
     globally
    0.68
    liness
    0.67
    ahime
    0.66
     ahead
    0.65
     internationally
    0.65
    ppo
    0.65
     domestically
    0.65
    Activations Density 0.395%

    No Known Activations