© 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. 18753
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or clauses related to a liberal agenda

    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
    eport
    -0.58
    ãĥīãĥ©
    -0.58
    adelphia
    -0.54
     golf
    -0.53
    irie
    -0.53
     mall
    -0.51
    Optional
    -0.51
     Moines
    -0.50
    iple
    -0.50
    mos
    -0.49
    POSITIVE LOGITS
     namely
    1.25
    especially
    0.99
     albeit
    0.98
     culminating
    0.93
     especially
    0.92
    particularly
    0.90
     lest
    0.89
     viz
    0.88
     particularly
    0.88
     irrespective
    0.87
    Activations Density 0.479%

    No Known Activations