INDEX

Explanations

phrases related to endorsements or recommendations

oai_token-act-pair · gpt-3.5-turbo

terms related to endorsements

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

rooms

-0.74

istics

-0.72

fare

-0.71

IRO

-0.70

folk

-0.69

awar

-0.69

istic

-0.69

atan

-0.67

gm

-0.66

brance

-0.66

POSITIVE LOGITS

 endorsing

1.12

 endorsements

1.09

 endorsement

1.00

 endorse

0.97

 endorsed

0.93

 candidate

0.82

eering

0.82

 loyalty

0.79

hovah

0.78

 endors

0.77

Activations Density 0.033%

phrases related to endorsements or recommendations

terms related to endorsements

No Comments

No Known Activations