© 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. 6-RES-JB
    11. 774
    Prev
    Next
    INDEX
    Explanations

    phrases related to timing, scheduling, or the ability to take action at any given point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the words "any" and "some" in relation to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.69
    sylv
    -0.63
     Lank
    -0.63
    lance
    -0.61
    ption
    -0.61
    ptive
    -0.60
    keeper
    -0.59
    keepers
    -0.59
     McGee
    -0.58
    inals
    -0.58
    POSITIVE LOGITS
     behest
    1.27
     expense
    1.13
     intersections
    1.01
     outset
    1.00
     discretion
    0.94
     helm
    0.93
     glance
    0.89
     speeds
    0.88
     whim
    0.84
     disposal
    0.84
    Activations Density 0.135%

    No Known Activations