INDEX

Explanations

instances of the verb "show."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Brito

-0.84

 Balt

-0.72

 Petra

-0.69

Spacing

-0.69

 lápiz

-0.69

 solitario

-0.68

zünd

-0.67

 esenciales

-0.66

cznym

-0.65

 Bernstein

-0.65

POSITIVE LOGITS

 Shows

2.13

 shows

2.08

shows

2.05

 Showing

2.03

 SHOWING

2.03

Shows

2.02

 SHOW

2.01

SHOW

2.00

 showing

1.99

 show

1.99

Activations Density 0.142%

instances of the verb "show."

No Comments

No Known Activations