INDEX

Explanations

references to specific numeric values or metrics

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

"at least"

np_acts-logits-general · gemini-2.0-flash

at least

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 nahilalakip

-0.98

脚注の使い方

-0.89

AlterField

-0.78

NewLabel

-0.77

 Paglinawan

-0.77

]")]

-0.77

ագրություններ

-0.77

ьаж

-0.76

исленность

-0.76

ModelForm

-0.76

POSITIVE LOGITS

 least

1.66

 LEAST

1.06

least

1.02

 Least

1.00

 lease

0.96

Least

0.92

 leaſt

0.87

le

0.84

 lest

0.73

 menos

0.71

Activations Density 0.144%

references to specific numeric values or metrics

"at least"

at least

No Comments

No Known Activations