INDEX

Explanations

references to individuals or groups

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

"Who" followed by a verb

np_acts-logits-general · gemini-2.0-flash

identifying who does what

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArrowToggle

-0.70

 رہ

-0.64

///</

-0.59

 steg

-0.55

le

-0.54

 Lyman

-0.54

 Berech

-0.54

 Stow

-0.54

Eis

-0.53

 Radcliffe

-0.53

POSITIVE LOGITS

who

1.35

WHO

1.04

Who

1.01

who

0.95

 whom

0.91

adeloupe

0.90

duled

0.89

Who

0.89

Whoosh

0.89

 którzy

0.88

Activations Density 0.074%

references to individuals or groups

"Who" followed by a verb

identifying who does what

No Comments

No Known Activations