INDEX

Explanations

key nouns and phrases related to significant entities or themes in discussions

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>

-2.60

-0.68

-0.67

-0.66

sizeCache

-0.65

InjectMocks

-0.64

-0.62

POSITIVE LOGITS

 chrysler

1.99

 lamborghini

1.87

 increa

1.87

 affor

1.86

 lidl

1.82

 beverly

1.81

 isuzu

1.73

fta

1.72

 maneu

1.71

 stockholm

1.71

Activations Density 0.573%

key nouns and phrases related to significant entities or themes in discussions

No Comments

No Known Activations