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. 12189
    Prev
    Next
    INDEX
    Explanations

    words related to empathy and kindness towards others, particularly emphasizing compassion

    oai_token-act-pair · gpt-3.5-turbo

    references to compassion 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
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.76
     Bam
    -0.76
    kj
    -0.72
    jong
    -0.72
    hof
    -0.64
    paces
    -0.64
     Rite
    -0.64
    wagen
    -0.63
    ORN
    -0.62
    azeera
    -0.62
    POSITIVE LOGITS
    ately
    1.06
    iously
    0.82
    giving
    0.81
     laureate
    0.80
    itably
    0.78
    ãĥĨãĤ£
    0.78
    lication
    0.78
    rehend
    0.77
     compassionate
    0.77
    udence
    0.74
    Activations Density 0.022%

    No Known Activations