INDEX

Explanations

words related to variations, differences, and ranges of values

oai_token-act-pair · gpt-3.5-turbo

expressions indicating variability or differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

stra

-0.78

Bern

-0.74

tur

-0.74

zyk

-0.74

swick

-0.70

çĦ

-0.69

odore

-0.68

Assembly

-0.67

WI

-0.66

ving

-0.66

POSITIVE LOGITS

 wildly

1.04

 degrees

0.94

 considerably

0.93

 depending

0.92

 markedly

0.91

 widely

0.91

 enormously

0.91

 geographically

0.90

 materially

0.89

ially

0.88

Activations Density 0.074%

words related to variations, differences, and ranges of values

expressions indicating variability or differences

No Comments

No Known Activations