© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    6. 9154
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or evaluations, particularly with words like "worst," "best," "certainly," and "good."

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments or criticisms

    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
     Accountability
    -0.47
     Talks
    -0.46
    CHAT
    -0.46
     Responsibility
    -0.45
     Dialogue
    -0.43
     Jude
    -0.41
     Wikimedia
    -0.41
     Culture
    -0.41
     Faul
    -0.40
     Investigative
    -0.40
    POSITIVE LOGITS
     suffice
    0.55
    uable
    0.53
    iatus
    0.51
    esides
    0.49
    ecided
    0.48
     bother
    0.48
     detract
    0.47
    ean
    0.46
     imaginable
    0.44
     dissu
    0.44
    Activations Density 5.730%

    No Known Activations