INDEX

Explanations

instances of the pronoun "I"

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

Token "i" followed by a variety of words

np_acts-logits-general · gemini-2.0-flash

i.e. or common abbreviations

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

CloseOperation

-0.64

 مشين

-0.57

struzioni

-0.54

FormTagHelper

-0.53

embeddings

-0.52

AnimationsModule

-0.52

']),

-0.51

HWND

-0.51

bunya

-0.49

?}",

-0.49

POSITIVE LOGITS

 iVar

0.65

rene

0.58

 iArr

0.58

ніципалі

0.57

pso

0.49

ffy

0.49

 MainAxisSize

0.49

OrBuilder

0.49

 venuto

0.48

$_['

0.48

Activations Density 0.152%

instances of the pronoun "I"

Token "i" followed by a variety of words

i.e. or common abbreviations

No Comments

No Known Activations