INDEX

Explanations

adjectives related to opinions or criticisms

oai_token-act-pair · gpt-3.5-turbo

instances of complex or nuanced opinions and observations

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

UF

-0.77

asio

-0.76

swick

-0.74

bilt

-0.73

tz

-0.69

EStream

-0.68

SHIP

-0.68

ioxide

-0.68

aha

-0.66

OME

-0.65

POSITIVE LOGITS

 albeit

1.15

but

0.94

 though

0.90

 however

0.90

 although

0.86

huh

0.82

albeit

0.81

 whereas

0.80

 namely

0.78

 except

0.77

Activations Density 0.260%

adjectives related to opinions or criticisms

instances of complex or nuanced opinions and observations

No Comments

No Known Activations