© 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. 10-RES-JB
    11. 14051
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reserve" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "reserve" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acles
    -0.82
    tra
    -0.67
    romeda
    -0.67
    src
    -0.67
    fixes
    -0.66
    Īè
    -0.65
    »Ĵ
    -0.65
    ento
    -0.64
     Luther
    -0.64
    iop
    -0.63
    POSITIVE LOGITS
    oir
    0.83
     reserve
    0.77
     Reserve
    0.76
    folios
    0.73
     Royale
    0.68
     stockpile
    0.67
    ritional
    0.67
     reserves
    0.67
    Bank
    0.66
     seating
    0.66
    Activations Density 0.047%

    No Known Activations