INDEX

Explanations

ratings, awards, and evaluations related to films and restaurants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ViewImports

-0.67

BeginContext

-0.58

 AssemblyCompany

-0.55

 חיצוניים

-0.51

posedge

-0.51

 fumée

-0.51

XtraBars

-0.48

 typedef

-0.48

 noqa

-0.47

\{\\

-0.47

POSITIVE LOGITS

 star

2.64

 stars

2.53

 Star

2.18

star

2.18

stars

2.08

 Stars

2.08

Star

2.06

 STAR

1.96

Stars

1.92

 estrellas

1.90

Activations Density 0.206%

ratings, awards, and evaluations related to films and restaurants

No Comments

No Known Activations