© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 7976
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or urgency

    oai_token-act-pair · gpt-3.5-turbo

    present tense and past tense forms of the verb "to be" and related expressions

    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
    ESE
    -0.70
     Previous
    -0.68
     Moves
    -0.65
    chuk
    -0.62
    iculture
    -0.61
    arel
    -0.61
    imental
    -0.60
     Purchase
    -0.60
    atown
    -0.60
    dds
    -0.59
    POSITIVE LOGITS
     accordingly
    1.22
     consequently
    1.12
     thereafter
    1.06
     alike
    1.00
     therefore
    0.91
     therein
    0.86
     certainly
    0.84
     thereof
    0.84
     promptly
    0.82
     definitely
    0.81
    Activations Density 0.411%

    No Known Activations