INDEX

Explanations

statements where the individual expresses emotional responses

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was," indicating past experiences or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

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

 entails

-0.69

 Current

-0.67

 Extend

-0.66

 Various

-0.65

 Highlands

-0.65

 Which

-0.65

 Users

-0.64

oyle

-0.63

 Reduce

-0.62

rates

-0.60

POSITIVE LOGITS

 able

1.14

 fortunate

1.09

 unable

1.05

 afraid

1.04

 supposed

1.03

 hoping

1.02

 lucky

1.02

 glad

1.02

 expecting

1.01

 aware

0.98

Activations Density 0.187%

statements where the individual expresses emotional responses

instances of the verb "was," indicating past experiences or actions

No Comments

No Known Activations