INDEX

Explanations

phrases related to detailed descriptions or narratives of events or locations

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

 minimalis

-0.86

 kosme

-0.79

 tanong

-0.78

 Souha

-0.77

 kompati

-0.77

 quæ

-0.76

 keramik

-0.73

 susun

-0.72

 Mejía

-0.72

 ejus

-0.72

POSITIVE LOGITS

 recording

0.72

 recordings

0.70

 recorded

0.67

 archiving

0.65

 record

0.65

 records

0.64

 keepsake

0.62

recording

0.62

recorded

0.61

 posterity

0.61

Activations Density 0.563%

phrases related to detailed descriptions or narratives of events or locations

No Comments

No Known Activations