© 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. 0-RES-JB
    11. 23108
    Prev
    Next
    INDEX
    Explanations

    software-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and properties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nod
    -0.97
     bow
    -0.94
     bound
    -0.85
     entry
    -0.85
     score
    -0.85
     feed
    -0.83
     thr
    -0.83
     finish
    -0.82
     pad
    -0.81
     experience
    -0.81
    POSITIVE LOGITS
    evidence
    1.74
    research
    1.71
    model
    1.70
    events
    1.70
    network
    1.69
    pressure
    1.68
    contact
    1.68
    volume
    1.67
    history
    1.66
    weapons
    1.66
    Activations Density 0.147%

    No Known Activations