Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5136
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to ire or anger

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ir" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 5 - anger

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.84
    zzo
    -0.73
    hetti
    -0.72
    soDeliveryDate
    -0.72
     Parad
    -0.70
     Halls
    -0.68
     Opera
    -0.67
    ezvous
    -0.66
    ership
    -0.65
     Remastered
    -0.65
    POSITIVE LOGITS
    idium
    1.02
    cles
    0.98
    ked
    0.91
    acet
    0.86
    ilateral
    0.81
    respective
    0.80
    itably
    0.79
    respons
    0.79
    religious
    0.78
    acial
    0.78
    Activations Density 0.009%

    No Known Activations