© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 2609
    Prev
    Next
    INDEX
    Explanations

    phrases related to advertising and promotions, and also mentions of medical trials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advertising and marketing

    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
    vic
    -0.69
    âĵĺ
    -0.65
    ermanent
    -0.63
     reckoning
    -0.63
     Detected
    -0.62
    nette
    -0.60
    aho
    -0.60
    20439
    -0.60
    cano
    -0.60
    Pg
    -0.59
    POSITIVE LOGITS
    eers
    0.80
    orial
    0.77
    uca
    0.77
    eering
    0.76
    ises
    0.76
    ONSORED
    0.75
    interstitial
    0.74
    inently
    0.74
    aeper
    0.71
    igslist
    0.71
    Activations Density 0.077%

    No Known Activations