INDEX

Explanations

comparative statements indicating superiority or complexity

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

comparisons where one thing is considered to be more significant or powerful than another

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

imity

-0.95

EMENT

-0.79

autions

-0.76

bilt

-0.74

 Juda

-0.74

antage

-0.71

erman

-0.70

uto

-0.68

ISSION

-0.66

ance

-0.66

POSITIVE LOGITS

 usual

1.02

 ever

0.81

 anything

0.80

 placebo

0.77

 ours

0.72

average

0.69

 average

0.68

acles

0.67

 others

0.67

 anybody

0.66

Activations Density 0.065%

comparative statements indicating superiority or complexity

comparisons where one thing is considered to be more significant or powerful than another

No Comments

No Known Activations