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. 12774
    Prev
    Next
    INDEX
    Explanations

    conditional statements indicating a hypothetical situation or consequence

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements expressing hypothetical situations

    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
     KR
    -0.72
    anka
    -0.65
    iates
    -0.62
    atl
    -0.62
    kin
    -0.60
     receptions
    -0.60
     millenn
    -0.60
     adolesc
    -0.60
     hijab
    -0.59
    UFF
    -0.57
    POSITIVE LOGITS
    rection
    0.89
     surely
    0.86
     automatically
    0.86
     certainly
    0.83
     sooner
    0.79
     undoubtedly
    0.78
     likely
    0.77
     become
    0.77
     probably
    0.76
     definitely
    0.75
    Activations Density 0.206%

    No Known Activations