© 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. 22612
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a specific proper noun 'alk'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific name or term related to a field of study or individual involved in research

    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
     Staples
    -0.66
     understatement
    -0.65
    ============
    -0.64
    PDATE
    -0.64
     circumstance
    -0.63
     medically
    -0.63
    ACTED
    -0.62
    ALLY
    -0.62
     CES
    -0.60
    ======
    -0.60
    POSITIVE LOGITS
    enburg
    1.06
    alk
    1.06
    owitz
    1.06
    enstein
    1.05
    ipedia
    1.03
    edIn
    0.93
    ers
    0.92
    reath
    0.91
    erness
    0.91
    ering
    0.91
    Activations Density 0.017%

    No Known Activations