© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1729
    Prev
    Next
    INDEX
    Explanations

    phrases related to social, political, and ideological discourse

    oai_token-act-pair · gpt-3.5-turbo

    references to social and economic class issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sid
    -0.77
    ety
    -0.72
    heast
    -0.69
     crunch
    -0.68
    rament
    -0.65
     pric
    -0.62
     meltdown
    -0.61
     pricey
    -0.61
    UFC
    -0.60
    wire
    -0.60
    POSITIVE LOGITS
     namely
    1.26
     albeit
    1.16
     etc
    1.13
     although
    1.11
     moreover
    1.07
     wherein
    1.07
     however
    1.05
     whilst
    1.03
     insofar
    1.02
     whereas
    1.02
    Activations Density 1.047%

    No Known Activations