INDEX

Explanations

positive sentiments and successful outcomes

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

instances of positive experiences and outcomes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

requires

-0.76

 impunity

-0.66

İĭ

-0.63

eware

-0.59

Reference

-0.58

CFR

-0.58

icons

-0.58

cknow

-0.58

osate

-0.56

 heirs

-0.56

POSITIVE LOGITS

 yesterday

1.04

 last

1.01

 haha

0.95

 initially

0.91

 beforehand

0.91

 afterwards

0.88

last

0.86

 afterward

0.82

 during

0.79

 LAST

0.78

Activations Density 0.801%

positive sentiments and successful outcomes

instances of positive experiences and outcomes

No Comments

No Known Activations