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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 15163
    Prev
    Next
    INDEX
    Explanations

    phrases related to the influence of various factors on a situation or outcome, such as medical conditions, community sentiments, and decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to influence and significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.72
    ISO
    -0.70
     Seym
    -0.69
     Orbit
    -0.65
    afety
    -0.64
    olitan
    -0.62
    iannopoulos
    -0.61
     Carbuncle
    -0.60
    edom
    -0.60
    arus
    -0.59
    POSITIVE LOGITS
     motivating
    1.15
     determining
    1.05
     influencing
    1.02
     shaping
    1.01
     helping
    0.96
     towards
    0.88
     deciding
    0.88
     contributing
    0.87
     in
    0.86
     impacting
    0.86
    Activations Density 0.136%

    No Known Activations