© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2877
    Prev
    Next
    INDEX
    Explanations

    words related to electrical outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of outlets, including media and electrical sources

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

    No Comments

    Negative Logits
    heed
    -0.79
    eric
    -0.76
    aah
    -0.70
    avery
    -0.66
     Feather
    -0.63
    ohan
    -0.61
     Griffith
    -0.60
    grave
    -0.60
    Engineers
    -0.60
     plague
    -0.58
    POSITIVE LOGITS
     outlet
    1.29
     outlets
    1.14
    swick
    0.81
    ="#
    0.76
    eval
    0.69
    icago
    0.65
     organs
    0.65
    media
    0.65
    stadt
    0.64
    izen
    0.62
    Activations Density 0.013%

    No Known Activations