INDEX

Explanations

the word "new" or 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vfill

-0.73

clearpage

-0.61

 ușor

-0.51

toPromise

-0.50

rdag

-0.47

 defaultdict

-0.46

dropna

-0.45

epsfig

-0.45

pentru

-0.44

("-");

-0.43

POSITIVE LOGITS

new

0.89

new

0.88

NEW

0.86

 fluo

0.86

New

0.85

 Darío

0.85

NEW

0.82

 Nuova

0.82

 anton

0.80

New

0.79

Activations Density 0.150%

the word "new" or related terms

No Comments

No Known Activations