INDEX

Explanations

words related to criticism or critique

oai_token-act-pair · gpt-3.5-turbo

references to critical commentary, particularly focusing on a specific critique of capitalism and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å§«

-0.85

DragonMagazine

-0.84

IELD

-0.79

lihood

-0.78

EMENT

-0.74

 Zucker

-0.71

Materials

-0.69

 Dragonbound

-0.68

eers

-0.68

 Awakens

-0.68

POSITIVE LOGITS

umb

1.22

umbled

1.16

umbs

1.10

ump

1.07

umbles

1.02

amping

1.00

umin

1.00

anked

0.99

udging

0.99

anking

0.98

Activations Density 0.009%

words related to criticism or critique

references to critical commentary, particularly focusing on a specific critique of capitalism and social issues

No Comments

No Known Activations