INDEX

Explanations

words related to evaluation or judgment

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate requirements, conditions, and notable qualities related to actions or attributes

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

ahime

-0.70

asus

-0.69

 Seymour

-0.68

 trave

-0.63

aper

-0.61

 conclud

-0.61

aniel

-0.61

Dan

-0.60

pload

-0.60

alks

-0.60

POSITIVE LOGITS

or

0.74

ulic

0.71

 interest

0.69

rawdownloadcloneembedreportprint

0.68

 functionality

0.67

matically

0.66

 realism

0.65

 emotion

0.64

 harm

0.63

 specific

0.63

Activations Density 0.442%

words related to evaluation or judgment

phrases that indicate requirements, conditions, and notable qualities related to actions or attributes

No Comments

No Known Activations