© 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. 8-RES-JB
    11. 7611
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about trustworthy news sources

    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
    ioned
    -0.72
    orem
    -0.66
    geist
    -0.65
    xton
    -0.64
    yg
    -0.63
     backlog
    -0.62
    ortium
    -0.61
    endon
    -0.61
    pic
    -0.61
    xus
    -0.60
    POSITIVE LOGITS
    independence
    0.67
     Currency
    0.66
     UNHCR
    0.65
    taboola
    0.63
    search
    0.62
    iframe
    0.62
    Afee
    0.62
    Subscribe
    0.61
     sources
    0.57
     subscribing
    0.57
    Activations Density 0.057%

    No Known Activations