INDEX

Explanations

phrases urging for reflection or consideration

oai_token-act-pair · gpt-3.5-turbo

directives or suggestions for actions that should be taken

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

 fungi

-0.65

 maze

-0.64

fra

-0.64

 inability

-0.62

fog

-0.61

 absentee

-0.61

Downloadha

-0.60

Boh

-0.60

 ozone

-0.59

uras

-0.58

POSITIVE LOGITS

 someday

0.93

 ASAP

0.82

 emulate

0.80

arna

0.76

èĢħ

0.73

cipled

0.70

raise

0.70

vised

0.69

rosso

0.68

fitting

0.68

Activations Density 0.176%

phrases urging for reflection or consideration

directives or suggestions for actions that should be taken

No Comments

No Known Activations