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. 3-RES-JB
    6. 2027
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving or providing something to someone

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating access, opportunities, and chances provided to individuals or groups

    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
    nel
    -0.70
     currents
    -0.63
    aten
    -0.62
     suicides
    -0.61
     Alps
    -0.58
     Alive
    -0.57
     Quarterly
    -0.57
     intrig
    -0.57
     BUS
    -0.57
     Walls
    -0.57
    POSITIVE LOGITS
    icum
    0.77
     berth
    0.72
     glimpse
    0.70
     chance
    0.68
    credit
    0.68
     opportunity
    0.68
    license
    0.67
     coveted
    0.67
     immunity
    0.66
     insight
    0.66
    Activations Density 0.317%

    No Known Activations