© 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. 0-RES-JB
    6. 2351
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocating or representing someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to advocacy or representation on behalf of individuals or groups

    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
    rough
    -0.60
     ate
    -0.59
     laughed
    -0.58
    wine
    -0.58
    alling
    -0.58
     cutoff
    -0.57
     Sims
    -0.57
     [+
    -0.56
    z
    -0.55
     cut
    -0.55
    POSITIVE LOGITS
     behalf
    4.39
     behest
    1.30
    etimes
    0.83
    Demand
    0.81
     redes
    0.81
     doorstep
    0.80
     unwitting
    0.78
    eworld
    0.76
    ufact
    0.76
     conduc
    0.75
    Activations Density 0.019%

    No Known Activations