© 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. 15236
    Prev
    Next
    INDEX
    Explanations

    words related to the field of technology or academic subjects ending in 'ology'

    oai_token-act-pair · gpt-3.5-turbo

    words related to various fields of study, particularly those ending in "ology."

    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
    kus
    -0.88
    imm
    -0.76
    arel
    -0.68
    ron
    -0.67
    iband
    -0.65
    azon
    -0.64
    rak
    -0.64
    CHA
    -0.64
    azaki
    -0.64
    imar
    -0.62
    POSITIVE LOGITS
    ology
    1.12
    ologies
    0.85
    ological
    0.85
    ologists
    0.81
    ologically
    0.77
    otherapy
    0.76
    ologic
    0.76
    ologist
    0.74
    OLOGY
    0.73
     Matters
    0.73
    Activations Density 0.026%

    No Known Activations