INDEX

Explanations

occurrences of the word "using."

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.07

 come

-0.72

ComponentModel

-0.70

Vegeu

-0.70

 came

-0.69

ValueGenerated

-0.66

won

-0.66

 comes

-0.66

 went

-0.66

 seek

-0.65

POSITIVE LOGITS

 increa

2.05

 thut

2.02

fta

2.01

 affor

1.92

 eiffel

1.91

 wien

1.90

 inev

1.89

aen

1.88

 stockholm

1.86

 maneu

1.84

Activations Density 0.082%

occurrences of the word "using."

No Comments

No Known Activations