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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 8493
    Prev
    Next
    INDEX
    Explanations

    names of political figures along with their political party affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals identified by the title "Senator" and the corresponding political party affiliation

    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
    ãĥ¼ãĥĨãĤ£
    -0.69
     CPR
    -0.69
     Totem
    -0.69
    enegger
    -0.68
    glers
    -0.68
     Dolphin
    -0.66
    grass
    -0.66
    -+-+
    -0.65
    éĹĺ
    -0.65
     Nieto
    -0.64
    POSITIVE LOGITS
    senal
    1.24
    ansom
    1.14
    acing
    1.12
    outing
    1.05
    haps
    1.04
    agnar
    1.04
    ework
    1.03
    ascal
    1.02
    anc
    1.01
    ach
    1.01
    Activations Density 0.033%

    No Known Activations