INDEX

Explanations

the word "ara" with high frequency 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Efq

-0.72

IndentedString

-0.72

UpInside

-0.67

StructEnd

-0.66

neſs

-0.65

ſelf

-0.64

 itſelf

-0.64

 Reſ

-0.64

 unſ

-0.63

 himſelf

-0.63

POSITIVE LOGITS

TC

1.03

ara

0.89

TC

0.81

tc

0.76

0.66

\{\\

0.66

Observe

0.65

tc

0.64

 Observe

0.61

0.59

Activations Density 0.091%

the word "ara" with high frequency in the text

No Comments

No Known Activations