INDEX

Explanations

phrases related to adding extra things or costs

oai_token-act-pair · gpt-3.5-turbo

monetary values and other quantifiable additional elements

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

apest

-0.66

CHAT

-0.63

ãĥ´

-0.61

 Abdel

-0.60

orig

-0.59

NYSE

-0.58

AGA

-0.57

TW

-0.57

 Defender

-0.56

POSITIVE LOGITS

 than

0.99

ricular

0.92

than

0.92

ources

0.79

iations

0.79

 layers

0.78

erous

0.78

redit

0.71

 arrivals

0.67

isites

0.66

Activations Density 0.173%

phrases related to adding extra things or costs

monetary values and other quantifiable additional elements

No Comments

No Known Activations