© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17410
    Prev
    Next
    INDEX
    Explanations

    words related to caring or concern for others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or caring towards others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jam
    -0.64
    ãĥĪ
    -0.64
    antha
    -0.60
    UES
    -0.59
     captcha
    -0.58
    Assembly
    -0.58
    NVIDIA
    -0.56
    uti
    -0.54
    GV
    -0.54
     scrambled
    -0.54
    POSITIVE LOGITS
    lessly
    1.24
     about
    1.15
     passionately
    1.09
     deeply
    1.04
     ABOUT
    1.01
    lessness
    0.96
    ened
    0.91
    about
    0.86
     enough
    0.85
    taker
    0.84
    Activations Density 0.027%

    No Known Activations