INDEX

Explanations

references to leadership roles and positions

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>

-2.67

-0.62

<?

-0.61

 springfox

-0.57

<?

-0.57

/*++

-0.56

 establish

-0.56

 invest

-0.56

 assume

-0.53

 interpret

-0.53

POSITIVE LOGITS

 unlaw

1.30

 quoique

1.24

 Minang

1.22

 increa

1.18

 affor

1.18

Head

1.15

 Head

1.14

 peppa

1.13

 emphat

1.12

 HEAD

1.12

Activations Density 0.060%

references to leadership roles and positions

No Comments

No Known Activations