INDEX

Explanations

expressions related to duties and responsibilities

oai_token-act-pair · gpt-3.5-turbo

references to responsibilities or roles defined as "job."

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

IFrame

Link

Negative Logits

vae

-0.73

 rumors

-0.67

 rumours

-0.66

AX

-0.63

 Kush

-0.61

 Missile

-0.60

Lot

-0.59

sent

-0.59

 Goth

-0.59

eros

-0.59

POSITIVE LOGITS

 responsibilities

0.88

 responsibility

0.86

 overseeing

0.83

 respons

0.82

verning

0.82

 duty

0.81

 protecting

0.81

 safegu

0.80

 obligation

0.78

 regulating

0.76

Activations Density 0.135%

expressions related to duties and responsibilities

references to responsibilities or roles defined as "job."

No Known Activations