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. 0-RES-JB
    6. 23477
    Prev
    Next
    INDEX
    Explanations

    proper names or titles, especially those related to politics and leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Chancellor" along with related descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benef
    -0.84
     benefiting
    -0.72
     benefited
    -0.69
    natureconservancy
    -0.69
     Medal
    -0.66
     entitled
    -0.61
    atin
    -0.60
    ogo
    -0.60
     performed
    -0.57
    step
    -0.57
    POSITIVE LOGITS
    llor
    4.81
    resa
    1.14
    usterity
    1.08
    intendent
    1.04
    skinned
    1.02
    rising
    0.98
    reme
    0.97
    theless
    0.96
    romeda
    0.96
    llan
    0.96
    Activations Density 0.021%

    No Known Activations