INDEX

Explanations

instances of the word "let" in various forms, indicating permission or suggestion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Agra

-0.86

 Aires

-0.82

findpost

-0.80

gående

-0.79

 Schulte

-0.76

ində

-0.75

ValueStyle

-0.75

}$

-0.75

Referencies

-0.75

 Morris

-0.74

POSITIVE LOGITS

LET

1.60

Let

1.59

Let

1.57

let

1.54

let

1.40

 lets

1.31

LET

1.30

 letting

1.24

Letting

1.20

 Letting

1.19

Activations Density 0.132%

instances of the word "let" in various forms, indicating permission or suggestion

No Comments

No Known Activations