INDEX

Explanations

proper nouns related to personal experiences and interactions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 brille

-0.88

 exé

-0.67

 sappi

-0.67

 tenda

-0.66

oretical

-0.65

 tappa

-0.63

 agrico

-0.62

 veneta

-0.62

 imprimée

-0.62

 allarg

-0.61

POSITIVE LOGITS

 herself

1.66

herself

1.46

her

1.25

she

1.15

 shes

1.10

 hers

1.04

حياتها

0.92

she

0.91

She

0.79

She

0.73

Activations Density 1.274%

proper nouns related to personal experiences and interactions

No Comments

No Known Activations