© 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. 6398
    Prev
    Next
    INDEX
    Explanations

    numerical thresholds or goals being reached

    oai_token-act-pair · gpt-3.5-turbo

    references to achieving goals or reaching milestones

    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
     preceded
    -0.62
     Tud
    -0.62
     Wed
    -0.61
    sbm
    -0.60
    oir
    -0.59
     betrayed
    -0.59
     alone
    -0.59
     Codex
    -0.57
     accompanies
    -0.57
     Chronicles
    -0.57
    POSITIVE LOGITS
     conclusion
    1.16
     heights
    1.16
     milestone
    1.12
     plateau
    1.06
     milestones
    1.03
     pinnacle
    1.02
     climax
    1.01
     halfway
    1.01
     destination
    1.00
     destinations
    0.98
    Activations Density 0.285%

    No Known Activations