INDEX

Explanations

the word "let" in different contexts, particularly when it indicates permission or allowance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ValueStyle

-0.79

Agra

-0.77

 Urbano

-0.77

RTDA

-0.77

isObject

-0.76

 Sambo

-0.74

 للاسماء

-0.74

cobra

-0.73

gamesh

-0.73

────────

-0.73

POSITIVE LOGITS

let

1.52

LET

1.45

Let

1.43

Let

1.41

 lets

1.30

Letting

1.21

let

1.21

 Letting

1.19

 letting

1.18

LET

1.15

Activations Density 0.115%

the word "let" in different contexts, particularly when it indicates permission or allowance

No Comments

No Known Activations