INDEX

Explanations

comparisons between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

references to comparative structures or phrases

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

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

 activ

-0.66

bys

-0.64

 ende

-0.63

aps

-0.62

 livest

-0.62

urai

-0.61

orr

-0.60

istries

-0.59

 lapt

-0.58

bucks

-0.57

POSITIVE LOGITS

 ordinary

0.86

 oneself

0.80

icial

0.73

 course

0.70

tains

0.67

 lowly

0.65

stood

0.63

wered

0.63

 ours

0.62

 average

0.61

Activations Density 0.043%

comparisons between different entities or concepts

references to comparative structures or phrases

No Comments

No Known Activations