© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 12622
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intensity or urgency

    oai_token-act-pair · gpt-3.5-turbo

    an unusual character or symbol in the text that may indicate formatting or error

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matic
    -0.95
    urated
    -0.84
    raints
    -0.82
    writers
    -0.80
     primates
    -0.75
     similarities
    -0.71
    igators
    -0.70
    orial
    -0.69
    engers
    -0.69
     Instr
    -0.69
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.23
    ľ
    1.02
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.02
    à©
    1.01
    ĺ
    0.97
    ĸ
    0.95
    ::::::::
    0.94
    Ķ
    0.94
    Ĺ
    0.94
    Ĩ
    0.93
    Activations Density 0.156%

    No Known Activations