© 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. 7678
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and official positions

    oai_token-act-pair · gpt-3.5-turbo

    content related to significant public figures and events

    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
    iating
    -0.57
     interven
    -0.55
     theirs
    -0.54
     reper
    -0.49
     foremost
    -0.49
    iates
    -0.48
     hoard
    -0.48
    ilty
    -0.47
    iated
    -0.47
     ownership
    -0.47
    POSITIVE LOGITS
    WASHINGTON
    1.02
    Untitled
    0.99
    Abstract
    0.98
    Description
    0.91
    Welcome
    0.88
    CLOSE
    0.88
    CTV
    0.87
    SAN
    0.85
    Overview
    0.84
    SCP
    0.82
    Activations Density 0.131%

    No Known Activations