INDEX

Explanations

references to the letter "p."

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>

-2.73

 intersper

-1.07

 quitted

-1.00

 shuddered

-0.97

 mustered

-0.94

 shivered

-0.91

 endow

-0.89

 rejoined

-0.87

 saluted

-0.87

 reinstate

-0.86

POSITIVE LOGITS

1.16

 quoique

0.90

 Pièces

0.86

 Outils

0.82

 jusque

0.81

 catég

0.80

 quelquefois

0.80

 justement

0.80

 énorm

0.78

Activations Density 0.045%

references to the letter "p."

No Comments

No Known Activations