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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8-RES-JB
    6. 20459
    Prev
    Next
    INDEX
    Explanations

    small and large monetary amounts mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exerc
    -0.96
     derog
    -0.81
     interf
    -0.75
     accomp
    -0.74
     Gors
    -0.73
     Vid
    -0.72
     Sed
    -0.71
     Glou
    -0.71
     constitu
    -0.70
     conven
    -0.69
    POSITIVE LOGITS
    $$
    1.26
    500
    1.22
    400
    1.21
    100
    1.20
    300
    1.20
    200
    1.17
    600
    1.14
    1000
    1.14
    false
    1.14
    150
    1.12
    Activations Density 0.082%

    No Known Activations