© 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. 1-RES-JB
    11. 1040
    Prev
    Next
    INDEX
    Explanations

    the word "itte" followed by a digit 8 or 9 in the text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific name or term related to a prominent individual or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rises
    -0.75
     prolong
    -0.66
     critically
    -0.64
    safety
    -0.64
     lapse
    -0.61
    sets
    -0.60
     leap
    -0.59
    ends
    -0.59
    acies
    -0.59
    ucks
    -0.59
    POSITIVE LOGITS
    itte
    1.27
    lli
    0.98
    tto
    0.98
    lla
    0.94
    etta
    0.92
    ements
    0.88
     LLP
    0.87
    lly
    0.86
    chnology
    0.85
    ":["
    0.84
    Activations Density 0.007%

    No Known Activations