© 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. 4-RES-JB
    6. 6588
    Prev
    Next
    INDEX
    Explanations

    references to a specific political party

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Liberal" in various contexts

    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
    bler
    -0.88
    $$
    -0.72
    âĵĺ
    -0.72
    schild
    -0.71
    pn
    -0.68
    ppa
    -0.68
    KT
    -0.67
    arding
    -0.66
    ...]
    -0.66
    IDER
    -0.66
    POSITIVE LOGITS
     Liberals
    0.79
     delinqu
    0.77
    aire
    0.77
    ism
    0.77
     Forces
    0.76
    ité
    0.75
     councillors
    0.75
     enclave
    0.74
     caucus
    0.73
    hift
    0.72
    Activations Density 0.010%

    No Known Activations