Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11162
    Prev
    Next
    INDEX
    Explanations

    keywords related to gender and political references

    oai_token-act-pair · gpt-3.5-turbo

    references to women and discussions surrounding women's issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compatible
    -0.63
     dotted
    -0.61
     scoring
    -0.57
     spect
    -0.57
     sensors
    -0.57
     enc
    -0.57
     needles
    -0.57
     options
    -0.56
     score
    -0.56
     orbital
    -0.55
    POSITIVE LOGITS
    woman
    4.32
    women
    2.79
    Woman
    2.10
    men
    2.05
    person
    1.96
    girl
    1.90
    man
    1.84
     Woman
    1.75
     woman
    1.63
    mans
    1.59
    Activations Density 0.008%

    No Known Activations