INDEX

Explanations

phrases related to slowing down or decelerating

oai_token-act-pair · gpt-3.5-turbo

expressions related to slowing down or reducing pace

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

Not in Any Lists

No Comments

Negative Logits

hold

-0.73

bern

-0.71

ocally

-0.68

Ô

-0.67

istani

-0.64

adel

-0.63

TY

-0.62

Ø§

-0.61

REL

-0.61

nor

-0.61

POSITIVE LOGITS

grading

0.93

 considerably

0.90

amina

0.81

graded

0.81

gradation

0.81

grades

0.79

 braking

0.76

baugh

0.75

 effectiveness

0.73

 tremendously

0.72

Activations Density 0.054%

phrases related to slowing down or decelerating

expressions related to slowing down or reducing pace

No Comments

No Known Activations