© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11513
    Prev
    Next
    INDEX
    Explanations

    guidelines or instructions related to social interactions and mentorship

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing kindness, individual needs, and supportive communication

    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
     piracy
    -0.84
     Armageddon
    -0.77
    terror
    -0.73
     smuggling
    -0.73
    piracy
    -0.72
    terrorist
    -0.70
     counterfe
    -0.69
     Die
    -0.69
     Murder
    -0.69
     hideous
    -0.68
    POSITIVE LOGITS
     mentors
    1.35
     counselors
    1.25
     facilit
    1.25
     interpersonal
    1.24
     mentor
    1.21
     counselor
    1.19
     rapport
    1.13
     ment
    1.13
     respectful
    1.08
     therapist
    1.07
    Activations Density 0.881%

    No Known Activations