INDEX

Explanations

references to specific individuals, possibly in academic or scientific contexts

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

Tokens starting with "Wo" or "wo"

np_acts-logits-general · gemini-2.0-flash

words starting with Wo

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

RectangleBorder

-0.66

 فريبيس

-0.65

Попис

-0.64

ities

-0.61

 itſelf

-0.60

 uintptr

-0.59

tabular

-0.59

hematical

-0.56

 <>",

-0.56

Spoljašnje

-0.55

POSITIVE LOGITS

Wo

0.79

Wo

0.73

 Wohl

0.70

Woj

0.70

vo

0.69

vo

0.69

Wor

0.67

 Woll

0.67

 Wolves

0.67

voz

0.67

Activations Density 0.098%

references to specific individuals, possibly in academic or scientific contexts

Tokens starting with "Wo" or "wo"

words starting with Wo

No Comments

No Known Activations