INDEX

Explanations

phrases within parentheses

oai_token-act-pair · gpt-3.5-turbo

parentheses and associated numerical sequences or acronyms

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

 blot

-0.86

 depress

-0.74

 impe

-0.74

 overd

-0.73

 nuts

-0.72

opsis

-0.72

 wrinkles

-0.72

 drift

-0.70

 spoilers

-0.69

 eternity

-0.69

POSITIVE LOGITS

formerly

1.21

UGC

1.21

CN

1.15

aka

1.15

PAC

1.09

PN

1.09

HUD

1.08

LIB

1.08

CF

1.08

AMS

1.07

Activations Density 0.073%

phrases within parentheses

parentheses and associated numerical sequences or acronyms

No Comments

No Known Activations