INDEX

Explanations

phrases related to disputes or disagreements

oai_token-act-pair · gpt-3.5-turbo

references to conflicts or disagreements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ISTER

-0.77

ococ

-0.75

append

-0.73

obb

-0.72

iffe

-0.71

asin

-0.71

iceps

-0.70

aea

-0.69

OVA

-0.69

ãģĨ

-0.69

POSITIVE LOGITS

 dispute

0.87

 disputed

0.80

 resolution

0.78

 disputes

0.78

 arising

0.74

 arises

0.71

 Resolution

0.71

 settlement

0.69

 adjud

0.67

 raging

0.67

Activations Density 0.027%

phrases related to disputes or disagreements

references to conflicts or disagreements

No Known Activations