© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 23204
    Prev
    Next
    INDEX
    Explanations

    financial terms and company names

    oai_token-act-pair · gpt-3.5-turbo

    references to financial companies and related economic topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.69
     thereof
    -0.63
    $.
    -0.53
     thereto
    -0.53
     cradle
    -0.52
    }.
    -0.51
     hereafter
    -0.49
    ]."
    -0.48
     signify
    -0.48
    omever
    -0.48
    POSITIVE LOGITS
     Profile
    0.71
     Edit
    0.59
     âĢº
    0.59
     Emails
    0.58
     Releases
    0.57
     âĵĺ
    0.55
     Cheong
    0.53
     WATCHED
    0.53
    ccording
    0.53
     Sets
    0.52
    Activations Density 2.082%

    No Known Activations