© 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. 2-RES-JB
    11. 1973
    Prev
    Next
    INDEX
    Explanations

    mentions of academic terms related to school semesters

    oai_token-act-pair · gpt-3.5-turbo

    references to academic semesters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourke
    -0.81
    omb
    -0.73
    acting
    -0.73
    gotten
    -0.71
    population
    -0.67
    generic
    -0.66
    rotein
    -0.65
    ACTED
    -0.65
    rosis
    -0.65
    irs
    -0.65
    POSITIVE LOGITS
    uates
    1.04
     semester
    0.94
     GPA
    0.94
    pai
    0.83
    VERTISEMENT
    0.83
    Course
    0.81
    uations
    0.76
     dorm
    0.76
     grades
    0.75
     lectures
    0.75
    Activations Density 0.009%

    No Known Activations