© 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. 1-RES-JB
    11. 3246
    Prev
    Next
    INDEX
    Explanations

    keywords related to anti-LGBT sentiments and legislation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti-gay sentiment and LGBTQ issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dur
    -0.63
     recurrent
    -0.63
     sol
    -0.62
    ç«
    -0.61
     Bei
    -0.60
     PST
    -0.60
     prototyp
    -0.59
    UME
    -0.59
     Annotations
    -0.59
     totality
    -0.59
    POSITIVE LOGITS
    gay
    1.09
    lord
    0.81
    xual
    0.78
    tons
    0.78
    enstein
    0.78
    osexual
    0.78
    chuk
    0.77
    zilla
    0.76
    bian
    0.76
    holes
    0.75
    Activations Density 0.007%

    No Known Activations