Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4083
    Prev
    Next
    INDEX
    Explanations

    evidence of large financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or financial figures in the text

    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
     worsh
    -0.58
     uncanny
    -0.56
     bang
    -0.56
     Nerd
    -0.55
     negativity
    -0.54
     prow
    -0.54
     behavi
    -0.53
     advoc
    -0.53
     beck
    -0.52
     gest
    -0.52
    POSITIVE LOGITS
    5
    1.33
    6
    1.27
    25
    1.24
    75
    1.23
    8
    1.23
    50
    1.21
    9
    1.19
    7
    1.18
    075
    1.17
    025
    1.15
    Activations Density 0.035%

    No Known Activations