© 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. 3-RES-JB
    11. 11979
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and schools, specifically focusing on pupil-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to students or learners in an educational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hive
    -0.66
    omes
    -0.65
     circumstance
    -0.63
    FTWARE
    -0.60
     cumbersome
    -0.60
    ISTORY
    -0.60
    ider
    -0.59
     deed
    -0.59
     normalized
    -0.58
     Reign
    -0.58
    POSITIVE LOGITS
     pupils
    1.07
     pupil
    0.93
    girls
    0.87
    folios
    0.78
    enary
    0.75
    hip
    0.74
    ilon
    0.74
    iless
    0.72
    lections
    0.72
    uates
    0.71
    Activations Density 0.011%

    No Known Activations