INDEX

Explanations

adjectives that describe the significance or impact of something

oai_token-act-pair · gpt-3.5-turbo

statements identifying key attributes or benefits of various subjects

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

urches

-0.68

iates

-0.67

ansen

-0.64

acists

-0.64

 Chero

-0.61

ults

-0.58

opted

-0.57

iate

-0.57

atl

-0.56

 Falls

-0.55

POSITIVE LOGITS

 undoubtedly

0.82

cussion

0.74

ovie

0.74

ometric

0.73

 indeed

0.71

 definitely

0.69

Reviewer

0.67

 actually

0.65

metics

0.65

not

0.64

Activations Density 0.132%

adjectives that describe the significance or impact of something

statements identifying key attributes or benefits of various subjects

No Comments

No Known Activations