INDEX

Explanations

phrases related to sacrifice or negative consequences

oai_token-act-pair · gpt-3.5-turbo

discussions about the concept of expense, particularly when it impacts others negatively

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

odes

-0.91

 Aval

-0.86

rams

-0.74

 Breaking

-0.68

estone

-0.67

nai

-0.66

Reviewed

-0.64

jong

-0.63

âĢ¢âĢ¢

-0.62

smoking

-0.62

POSITIVE LOGITS

 expense

1.22

itures

1.04

 expenses

0.87

 incurred

0.85

folios

0.84

 reimburse

0.81

iture

0.78

 expenditure

0.78

xual

0.77

atre

0.74

Activations Density 0.004%

phrases related to sacrifice or negative consequences

discussions about the concept of expense, particularly when it impacts others negatively

No Comments

No Known Activations