© 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. 10-RES-JB
    11. 6663
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideological viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ide" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.88
    lished
    -0.77
    iona
    -0.74
    ishable
    -0.72
    ions
    -0.71
    lishing
    -0.70
    ured
    -0.68
    ION
    -0.65
    thur
    -0.64
    ufact
    -0.63
    POSITIVE LOGITS
    gger
    0.96
    ll
    0.91
    creen
    0.85
    llo
    0.82
    OLOG
    0.79
    vice
    0.79
    lli
    0.77
    llan
    0.77
    lla
    0.77
    rer
    0.75
    Activations Density 0.046%

    No Known Activations