© 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. 0-RES-JB
    11. 16599
    Prev
    Next
    INDEX
    Explanations

    words related to providing reassurance or comfort

    oai_token-act-pair · gpt-3.5-turbo

    terms related to providing comfort and assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     degener
    -0.76
     ineligible
    -0.74
     piracy
    -0.73
     penalties
    -0.71
     spawn
    -0.70
     banned
    -0.70
     DU
    -0.70
     felony
    -0.69
     executed
    -0.67
     ranked
    -0.66
    POSITIVE LOGITS
     reassuring
    2.64
     comforting
    2.61
     soothing
    2.13
     warmth
    1.90
     reassure
    1.90
     reassured
    1.83
     comfort
    1.81
     consolation
    1.64
     calming
    1.58
    comfort
    1.55
    Activations Density 0.047%

    No Known Activations