INDEX

Explanations

finance-related terms or phrases

oai_token-act-pair · gpt-3.5-turbo

terms related to financial situations or financial health

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

hua

-0.77

 Nieto

-0.74

 Rousse

-0.73

lain

-0.73

rose

-0.73

 Pont

-0.72

Klu

-0.72

 quartz

-0.71

 Flesh

-0.69

dq

-0.69

POSITIVE LOGITS

 incentives

1.04

 incentive

1.03

 considerations

0.89

 autonomy

0.87

 upkeep

0.87

 rewards

0.86

 clout

0.86

 hardship

0.85

 resources

0.85

 disclosure

0.84

Activations Density 0.048%

finance-related terms or phrases

terms related to financial situations or financial health

No Comments

No Known Activations