© 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. 2-RES-JB
    11. 938
    Prev
    Next
    INDEX
    Explanations

    monetary amounts preceded by a currency symbol and/or followed by quantitative units or financial terms

    oai_token-act-pair · gpt-4-turbo

    phrases related to financial figures and amounts

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.71
     Silence
    -0.64
    oman
    -0.63
    itia
    -0.62
     Gaul
    -0.62
     deaf
    -0.62
    vid
    -0.61
     rhythms
    -0.60
    gha
    -0.60
    nosis
    -0.60
    POSITIVE LOGITS
    -$
    1.14
    /$
    1.02
     royalties
    0.92
     dollars
    0.91
     (£
    0.89
    billion
    0.88
     savings
    0.88
    pees
    0.87
     mortgages
    0.82
    advertising
    0.82
    Activations Density 1.052%

    No Known Activations