INDEX

Explanations

words related to spatial locations, especially in front of something

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

 pymysql

-0.84

 apprehen

-0.76

 vagu

-0.76

 intrigu

-0.76

 emphat

-0.74

 napoli

-0.74

 alberto

-0.74

 indescri

-0.73

 notori

-0.72

 Abbé

-0.72

POSITIVE LOGITS

front

0.87

 front

0.82

Front

0.77

 Front

0.74

 FRONT

0.74

FRONT

0.73

styleType

0.65

TagMode

0.61

 مرئيه

0.61

 الحره

0.61

Activations Density 0.033%

words related to spatial locations, especially in front of something

No Comments

No Known Activations