INDEX

Explanations

terms related to insider trading

oai_token-act-pair · gpt-3.5-turbo

terms related to insider trading in the context of finance and law

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

 Parenthood

-0.76

ammers

-0.76

amaz

-0.71

ensions

-0.70

interrupted

-0.68

oÄŁ

-0.66

ez

-0.66

oran

-0.65

 Archangel

-0.64

anic

-0.64

POSITIVE LOGITS

aucus

0.82

 insiders

0.82

holder

0.80

 insider

0.79

holders

0.75

clair

0.72

 workings

0.71

 Trading

0.68

obin

0.66

 informant

0.65

Activations Density 0.023%

terms related to insider trading

terms related to insider trading in the context of finance and law

No Comments

No Known Activations