INDEX

Explanations

brands and research-related terms

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

 sopr

-0.73

 purtroppo

-0.70

 peculi

-0.68

 ricor

-0.67

 inol

-0.64

 gius

-0.64

 anzi

-0.63

 piú

-0.62

 chiunque

-0.61

 parteci

-0.61

POSITIVE LOGITS

 whose

0.61

who

0.58

Charsets

0.54

toPromise

0.51

*++

0.51

dshaw

0.50

RectF

0.48

 themselves

0.47

 whom

0.47

hips

0.47

Activations Density 0.357%

brands and research-related terms

No Comments

No Known Activations