© 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. 4-RES-JB
    11. 14847
    Prev
    Next
    INDEX
    Explanations

    Specific words related to the profession of being a practitioner or practices carried out by practitioners

    oai_token-act-pair · gpt-3.5-turbo

    terms related to practical applications and practitioners in various fields

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

    No Comments

    Negative Logits
    mine
    -0.78
     Bom
    -0.71
    bum
    -0.71
    berry
    -0.70
    berries
    -0.70
    caps
    -0.67
     Rodgers
    -0.67
     Blazers
    -0.67
     peg
    -0.64
    by
    -0.64
    POSITIVE LOGITS
     practitioner
    1.07
    icum
    1.03
     practitioners
    1.00
    icing
    0.98
     pract
    0.98
    icion
    0.92
    Pract
    0.91
     Pract
    0.90
    icable
    0.85
    practice
    0.85
    Activations Density 0.016%

    No Known Activations