INDEX

Explanations

phrases that express uncertainty or qualification

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a sense of ambiguity or vagueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

iership

-0.85

ESE

-0.85

utherland

-0.82

ULTS

-0.80

ests

-0.78

eful

-0.76

BAT

-0.75

ACA

-0.75

umerable

-0.74

IAL

-0.73

POSITIVE LOGITS

 messed

1.02

 screwed

1.01

 fucked

0.91

 sucks

0.91

bum

0.90

 reminds

0.90

 neat

0.90

 sucked

0.86

 weird

0.84

 lame

0.83

Activations Density 0.049%

phrases that express uncertainty or qualification

phrases that indicate a sense of ambiguity or vagueness

No Comments

No Known Activations