© 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. 8-RES-JB
    11. 6422
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a large quantity or abundance of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating substantial quantities or concepts of excess or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endants
    -0.88
    artments
    -0.81
    ramid
    -0.80
    ħĭ
    -0.79
    ares
    -0.76
    pecially
    -0.75
    ospels
    -0.74
    ooters
    -0.74
    geons
    -0.73
    rank
    -0.70
    POSITIVE LOGITS
     misinformation
    1.08
     activity
    1.07
     firepower
    1.05
     attention
    1.05
     chatter
    1.04
     scrutiny
    1.04
     information
    1.02
     money
    1.01
     coverage
    1.00
     publicity
    1.00
    Activations Density 0.522%

    No Known Activations