© 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. 6-RES-JB
    11. 19775
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and their actions

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to President Obama and President Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anges
    -0.82
    olkien
    -0.81
    ragon
    -0.81
    lehem
    -0.79
    hari
    -0.78
    Reviewer
    -0.77
    cam
    -0.73
    Developer
    -0.73
    jun
    -0.73
     Kubrick
    -0.73
    POSITIVE LOGITS
     own
    1.22
     newest
    1.11
     penchant
    1.04
     insistence
    1.00
     signature
    1.00
     latest
    0.99
     foray
    0.97
     playbook
    0.94
     antics
    0.93
     predicament
    0.93
    Activations Density 0.162%

    No Known Activations