INDEX

Explanations

keywords related to technical instructions or steps

oai_token-act-pair · gpt-3.5-turbo

phrases related to technology, specifically printing and programming outputs

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

 Ethics

-0.75

 preempt

-0.72

 stake

-0.71

 upbringing

-0.71

 contem

-0.69

 legisl

-0.69

 derog

-0.69

istani

-0.68

 educ

-0.68

 economics

-0.67

POSITIVE LOGITS

 indistinguishable

0.92

 resembling

0.89

 noticeable

0.85

ptoms

0.81

 streaks

0.77

 noticeably

0.77

 shimmer

0.76

luster

0.75

ifferent

0.75

 usable

0.74

Activations Density 0.840%

keywords related to technical instructions or steps

phrases related to technology, specifically printing and programming outputs

No Comments

No Known Activations