© 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. 7-RES-JB
    11. 16720
    Prev
    Next
    INDEX
    Explanations

    references to the word 'Albany'

    oai_token-act-pair · gpt-3.5-turbo

    specific letter combinations or patterns, particularly involving the letter "b" and related phonetic or grapheme structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.67
    lde
    -0.67
     Cosponsors
    -0.66
    SHIP
    -0.64
    itiveness
    -0.63
    yip
    -0.63
    ancial
    -0.59
     REUTERS
    -0.59
    fw
    -0.58
    elines
    -0.57
    POSITIVE LOGITS
    azeera
    1.06
    arez
    0.90
    querque
    0.88
    aida
    0.80
    hyde
    0.79
    aeda
    0.78
    abet
    0.75
    Si
    0.71
    Qaeda
    0.70
     Decay
    0.70
    Activations Density 0.081%

    No Known Activations