INDEX

Explanations

the presence and frequency of the word "the" in various contexts

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

"The" followed by a capitalized word

np_acts-logits-general · gemini-2.0-flash

The [proper noun]

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.95

 itſelf

-0.91

 propOrder

-0.88

 Italijanski

-0.86

SharedDtor

-0.86

etheless

-0.85

 Houſe

-0.85

 Monfieur

-0.83

 Shakspeare

-0.83

 myſelf

-0.82

POSITIVE LOGITS

 following

0.95

 first

0.89

 best

0.88

 most

0.88

The

0.81

 final

0.81

 Great

0.80

<eos>

0.80

The

0.79

Activations Density 0.483%

the presence and frequency of the word "the" in various contexts

"The" followed by a capitalized word

The [proper noun]

No Comments

No Known Activations