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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 23683
    Prev
    Next
    INDEX
    Explanations

    mentions of monetary amounts

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or financial figures

    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
     exerc
    -0.90
     Gors
    -0.76
     metab
    -0.74
     Halls
    -0.72
    umbn
    -0.71
     Sed
    -0.70
     Redd
    -0.69
     Tid
    -0.69
     Tall
    -0.68
     appar
    -0.68
    POSITIVE LOGITS
    100
    1.18
    $$
    1.13
    500
    1.13
    150
    1.12
    250
    1.12
    300
    1.11
    200
    1.09
    600
    1.08
    USD
    1.07
    400
    1.06
    Activations Density 0.088%

    No Known Activations