INDEX

Explanations

words related to political decision-making and actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to political decision-making and personal risks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

selves

-0.81

 selves

-0.75

Origin

-0.68

 âĸĪ

-0.65

CLA

-0.65

monkey

-0.61

ï¸ı

-0.61

cause

-0.61

atos

-0.61

 unison

-0.60

POSITIVE LOGITS

 himself

1.45

his

1.18

 Himself

1.00

 reforms

1.00

 veto

0.98

 reelection

0.97

 appointing

0.97

 unilaterally

0.96

 aides

0.94

 Cabinet

0.94

Activations Density 0.636%

words related to political decision-making and actions

phrases related to political decision-making and personal risks

No Comments

No Known Activations