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. 1351
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety concerns and precautions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social issues and concerns

    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
    omever
    -0.68
    Untitled
    -0.68
    ayn
    -0.65
     ItemLevel
    -0.65
    Oracle
    -0.64
     [*
    -0.63
    ("
    -0.62
     exclaim
    -0.60
     wherein
    -0.60
    [[
    -0.60
    POSITIVE LOGITS
    ':
    0.87
    '?
    0.86
     Replay
    0.86
     Challenges
    0.78
     Approach
    0.78
     Concern
    0.76
    ?'
    0.73
     Own
    0.70
     Timeline
    0.69
     Potential
    0.68
    Activations Density 1.049%

    No Known Activations