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. 3-RES-JB
    6. 1713
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    oai_token-act-pair · gpt-3.5-turbo

    references to notable figures or events in historical or societal contexts

    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
    iquette
    -0.27
     Jessie
    -0.27
    Files
    -0.25
     glim
    -0.25
    iaries
    -0.24
    itialized
    -0.24
     Rena
    -0.24
     Mayo
    -0.23
     Carly
    -0.23
    urable
    -0.23
    POSITIVE LOGITS
    ĺħ
    0.32
    )).
    0.30
    )."
    0.30
     dracon
    0.30
    }.
    0.29
    .).
    0.28
    ]."
    0.28
    )))
    0.27
    ).[
    0.27
    ").
    0.27
    Activations Density 7.546%

    No Known Activations