INDEX

Explanations

references to scale or measurements in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.69

<?

-0.65

-0.61

 admit

-0.60

ⓧ

-0.59

put

-0.58

-0.56

 defend

-0.56

cup

-0.56

 cố

-0.54

POSITIVE LOGITS

 accla

1.53

 suspic

1.50

 ecru

1.47

 fatis

1.43

 jaya

1.40

 wien

1.40

 effe

1.40

 unwarran

1.39

 bandung

1.39

 nece

1.37

Activations Density 0.048%

references to scale or measurements in various contexts

No Comments

No Known Activations