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. 23400
    Prev
    Next
    INDEX
    Explanations

    terms related to various processes and actions, such as development, monitoring, training, installation, building, restoration, campaign, rescue, recovery, and registration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and activities in technology and emergency situations

    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
    yrics
    -0.79
    TextColor
    -0.76
    ĪĴ
    -0.75
     Gleaming
    -0.69
    stood
    -0.67
    othes
    -0.65
     Helpful
    -0.65
    onyms
    -0.63
    osponsors
    -0.61
    Desktop
    -0.61
    POSITIVE LOGITS
     process
    1.36
     programme
    1.31
     endeavor
    1.31
     spree
    1.30
     expedition
    1.24
     endeavour
    1.22
     mission
    1.21
     operation
    1.21
     campaign
    1.20
     phase
    1.20
    Activations Density 0.559%

    No Known Activations