© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19242
    Prev
    Next
    INDEX
    Explanations

    action verbs related to communication, decision-making, and management

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with discussions and organizational roles

    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
    ruary
    -0.84
    nery
    -0.83
    idon
    -0.81
    iness
    -0.81
    iosis
    -0.79
    weed
    -0.78
    syn
    -0.78
    ascript
    -0.77
    fi
    -0.76
    ternity
    -0.75
    POSITIVE LOGITS
     mechanism
    0.74
     agent
    0.74
     ability
    0.72
     grounds
    0.72
     rod
    0.71
     rink
    0.69
     electron
    0.68
     machine
    0.68
     circle
    0.68
     edge
    0.65
    Activations Density 0.275%

    No Known Activations