© 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. 1-RES-JB
    11. 16191
    Prev
    Next
    INDEX
    Explanations

    mentions of mentorship or being a mentor

    oai_token-act-pair · gpt-3.5-turbo

    references to mentors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irens
    -0.65
    lt
    -0.64
    ldon
    -0.61
    Copyright
    -0.61
    ternity
    -0.61
    scan
    -0.61
    large
    -0.61
    yg
    -0.61
    meal
    -0.60
    aque
    -0.59
    POSITIVE LOGITS
     mentor
    1.40
     mentors
    1.33
     tutor
    1.04
     ment
    0.95
     Ment
    0.90
    hesis
    0.88
     advisor
    0.86
     collaborator
    0.81
     Assist
    0.80
     tut
    0.80
    Activations Density 0.009%

    No Known Activations