INDEX

Explanations

phrases related to criticism or critique

oai_token-act-pair · gpt-3.5-turbo

instances of criticism towards people, organizations, or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aceae

-0.77

frog

-0.76

Ã¨re

-0.73

*.

-0.72

producing

-0.71

hots

-0.70

 toget

-0.70

tackle

-0.70

stable

-0.69

llular

-0.68

POSITIVE LOGITS

 portrayal

1.15

 lack

1.06

 inaction

1.05

 notion

1.04

 motives

1.01

 adequ

1.00

 legality

0.96

 hypocrisy

0.95

 validity

0.92

 legitimacy

0.92

Activations Density 0.272%

phrases related to criticism or critique

instances of criticism towards people, organizations, or actions

No Comments

No Known Activations