INDEX

Explanations

references to time periods, specifically months and years

oai_token-act-pair · gpt-4o-mini Triggered by @bot

time units

np_acts-logits-general · gemini-2.0-flash

month, hour, century

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Re

-0.56

//

-0.54

/**

-0.51

closedir

-0.49

Re

-0.47

 acceptez

-0.45

Br

-0.44

例文帳に追加

-0.44

lá

-0.43

uitable

-0.43

POSITIVE LOGITS

DockStyle

0.97

 Pound

0.89

parsedMessage

0.87

findpost

0.84

 purpoſe

0.82

Pound

0.81

 pound

0.81

 avoient

0.77

 postIndex

0.76

 ſever

0.76

Activations Density 0.296%

references to time periods, specifically months and years

time units

month, hour, century

No Comments

No Known Activations