© 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. 2-RES-JB
    11. 9477
    Prev
    Next
    INDEX
    Explanations

    email addresses, specifically those containing the sequence "podesta"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of proper nouns or names related to individuals, specifically those that are commonly associated with media or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.65
     neutrality
    -0.65
    lication
    -0.64
    pelled
    -0.64
    liners
    -0.63
    rified
    -0.63
     Boolean
    -0.62
     existential
    -0.62
    drawn
    -0.62
    sided
    -0.60
    POSITIVE LOGITS
    esta
    1.36
    ieri
    0.87
    ãĥ¼ãĥĨãĤ£
    0.83
     Luxem
    0.83
    UTION
    0.79
    utive
    0.78
    ppo
    0.77
    ption
    0.77
    zza
    0.76
    ERT
    0.76
    Activations Density 0.015%

    No Known Activations