INDEX

Explanations

phrases related to prevention or hindrance

oai_token-act-pair · gpt-3.5-turbo

phrases indicating prevention or obstacles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bush

-0.74

atl

-0.72

soDeliveryDate

-0.71

nob

-0.69

aic

-0.69

tops

-0.69

oct

-0.68

KC

-0.67

MON

-0.67

uid

-0.67

POSITIVE LOGITS

 accessing

1.03

 reaching

0.91

 completing

0.90

 obtaining

0.89

 achieving

0.87

 entering

0.83

 participating

0.83

 getting

0.82

 being

0.80

 taking

0.80

Activations Density 0.054%

phrases related to prevention or hindrance

phrases indicating prevention or obstacles

No Comments

No Known Activations