© 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. 4-RES-JB
    11. 2749
    Prev
    Next
    INDEX
    Explanations

    terms related to various topics such as legislation, politicians, political entities, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    topics related to political and social issues, particularly those involving public health and community focus

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

    No Comments

    Negative Logits
    .).
    -0.75
     respectively
    -0.68
    )).
    -0.65
    '.
    -0.63
    Downloadha
    -0.61
     thereof
    -0.60
    Flag
    -0.58
    .'"
    -0.58
    '."
    -0.57
    ).
    -0.57
    POSITIVE LOGITS
     terminology
    0.66
     explanations
    0.57
     Fail
    0.55
     Analytics
    0.54
    urious
    0.53
    pal
    0.51
     Webs
    0.50
    NET
    0.50
     aback
    0.49
    earch
    0.49
    Activations Density 1.288%

    No Known Activations