© 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. 20294
    Prev
    Next
    INDEX
    Explanations

    terms related to caregiving or caretaking

    oai_token-act-pair · gpt-3.5-turbo

    mentions of caregiving or care-related themes

    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
    ãĥĥãĥī
    -0.82
    akedown
    -0.64
     rand
    -0.64
    å°Ĩ
    -0.63
    ãĥ³ãĤ¸
    -0.63
    UE
    -0.60
    UES
    -0.59
     toast
    -0.58
     debugging
    -0.58
    uments
    -0.58
    POSITIVE LOGITS
    taker
    1.80
    giving
    1.43
    taking
    1.33
    lessness
    1.20
    free
    1.19
    lessly
    1.14
    fully
    1.12
    worn
    1.06
    ening
    1.06
    ful
    0.96
    Activations Density 0.029%

    No Known Activations