© 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. 462
    Prev
    Next
    INDEX
    Explanations

    phrases related to discouraging or dissuading others from certain actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discouragement or dissuasion

    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
    ammy
    -0.88
    iop
    -0.77
    odore
    -0.72
    uben
    -0.71
     Nanto
    -0.69
    esome
    -0.68
    akening
    -0.68
    ophon
    -0.68
    lene
    -0.68
    thren
    -0.68
    POSITIVE LOGITS
    ministic
    0.96
     discour
    0.91
     discouraged
    0.86
     discouraging
    0.86
     discourage
    0.83
     dissu
    0.82
    GGGGGGGG
    0.74
     vacc
    0.71
    minist
    0.71
     unwanted
    0.71
    Activations Density 0.017%

    No Known Activations