INDEX

Explanations

phrases indicating intensification or accumulation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating worsening situations or exacerbation of issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ufact

-0.88

leans

-0.69

ologue

-0.68

 boards

-0.66

icle

-0.65

inates

-0.65

utics

-0.65

pload

-0.65

atics

-0.64

aceutical

-0.63

POSITIVE LOGITS

 suspicions

1.21

 tensions

1.18

 tension

1.08

 mistrust

1.08

 frustration

1.07

 confusion

1.07

 frustrations

1.03

 distrust

1.01

 misery

1.00

 uncertainty

0.99

Activations Density 0.192%

phrases indicating intensification or accumulation

phrases indicating worsening situations or exacerbation of issues

No Comments

No Known Activations