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. 6-RES-JB
    6. 1823
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and economic discussions, including long-term fiscal discipline and specific social issues such as same-sex marriage

    oai_token-act-pair · gpt-3.5-turbo

    discourses related to economic stability and policy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibrary
    -0.58
     Aval
    -0.56
     TODAY
    -0.55
     Emblem
    -0.53
     AND
    -0.52
    ikk
    -0.52
    cture
    -0.51
    ortium
    -0.49
    ãĤ°
    -0.49
     Yiannopoulos
    -0.48
    POSITIVE LOGITS
     alike
    1.40
     respectively
    1.13
     thereof
    1.07
     versa
    0.92
     thereto
    0.80
     accordingly
    0.79
     therein
    0.78
     thereafter
    0.78
    ).[
    0.65
    depending
    0.65
    Activations Density 1.506%

    No Known Activations