INDEX

Explanations

various symbols and formatting characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 Kalman

-0.75

 Thelma

-0.69

 ſta

-0.68

 obfer

-0.68

行った

-0.67

 whofe

-0.67

 ejus

-0.67

 poffible

-0.67

出場

-0.65

 Olin

-0.65

POSITIVE LOGITS

に

1.06

面に

1.03

ものに

0.92

月に

0.92

りに

0.90

に

0.89

かに

0.88

さに

0.87

時間に

0.86

기에

0.85

Activations Density 0.027%

various symbols and formatting characters in the text

No Comments

No Known Activations