© 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. 7-RES-JB
    11. 19110
    Prev
    Next
    INDEX
    Explanations

    political and organizational terms like "Senate", "independent", "appeal", "non-profit", and "degree"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government, professional qualifications, and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.89
     circles
    -0.75
     merchants
    -0.71
    lees
    -0.69
    redients
    -0.68
     Bits
    -0.68
    itudes
    -0.65
    nels
    -0.65
    ometimes
    -0.64
    bits
    -0.64
    POSITIVE LOGITS
     foothold
    1.01
     solution
    0.92
     berth
    0.90
     replacement
    0.84
     outlet
    0.83
     apology
    0.82
     endorsement
    0.79
     successor
    0.79
     representation
    0.79
     explanation
    0.78
    Activations Density 0.580%

    No Known Activations