INDEX

Explanations

references to "small" in various contexts

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

"small"

np_acts-logits-general · gemini-2.0-flash

small followed by word

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

PYX

-0.68

CodeAttribute

-0.63

 للمعارف

-0.61

WithIdentifier

-0.60

 utafitiHapana

-0.59

WriteBarrier

-0.58

 intStringLen

-0.58

AndEndTag

-0.58

ільки

-0.57

üyada

-0.57

POSITIVE LOGITS

 Small

0.89

Small

0.88

pox

0.81

 SMALL

0.81

small

0.79

 small

0.79

 tiny

0.78

SMALL

0.75

pox

0.72

(<

0.71

Activations Density 0.178%

references to "small" in various contexts

"small"

small followed by word

No Comments

No Known Activations