INDEX

Explanations

phrases related to vulnerabilities or weaknesses

oai_token-act-pair · gpt-3.5-turbo

phrases indicating measurements or quantities associated with "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Kills

-0.98

çīĪ

-0.82

days

-0.74

eus

-0.69

Requirements

-0.68

stones

-0.68

 Uses

-0.68

acea

-0.67

Ô

-0.67

Brave

-0.66

POSITIVE LOGITS

 varying

0.95

 differing

0.80

 contention

0.77

 interest

0.74

 concentrated

0.72

 disparate

0.71

sembly

0.70

 assorted

0.70

 resistance

0.70

 intrigue

0.69

Activations Density 0.237%

phrases related to vulnerabilities or weaknesses

phrases indicating measurements or quantities associated with "of."

No Comments

No Known Activations