INDEX

Explanations

instances of the word "compared" and its variations

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

"compared" followed by "with" or "to"

np_acts-logits-general · gemini-2.0-flash

compared with or to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 فريبيس

-0.82

 يتيمه

-0.76

 AssemblyVersion

-0.75

SequentialGroup

-0.71

حياته

-0.68

httphttps

-0.68

Jeografia

-0.62

حياتها

-0.62

Cyfeiriadau

-0.61

StructEnd

-0.61

POSITIVE LOGITS

 favorably

0.84

 favourably

0.79

 apples

0.74

 against

0.71

TagHelper

0.61

against

0.60

之下

0.59

 Benchmark

0.55

 sánh

0.55

Against

0.55

Activations Density 0.086%

instances of the word "compared" and its variations

"compared" followed by "with" or "to"

compared with or to

No Comments

No Known Activations