INDEX

Explanations

phrases indicating references or citations within a text

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

that appear before other words

np_acts-logits-general · gemini-2.0-flash

established, exist, gone, referencia

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 themſelves

-0.59

 itſelf

-0.56

 Whig

-0.55

 Ambiental

-0.55

 fann

-0.54

irsi

-0.54

 himſelf

-0.54

 Himself

-0.54

 Kenobi

-0.52

EEC

-0.52

POSITIVE LOGITS

the

0.88

NameInMap

0.64

addComponent

0.63

 noqa

0.61

 CreateTagHelper

0.60

tahui

0.59

 there

0.58

 another

0.57

 Comes

0.56

Activations Density 0.079%

phrases indicating references or citations within a text

that appear before other words

established, exist, gone, referencia

No Comments

No Known Activations