INDEX

Explanations

dates or years

oai_token-act-pair · gpt-3.5-turbo

specific years mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 nearest

-0.62

 porous

-0.61

hed

-0.59

 fault

-0.59

 incap

-0.59

 jurisd

-0.58

 contingency

-0.58

 whipping

-0.57

 hypocr

-0.57

weak

-0.56

POSITIVE LOGITS

å¹

0.82

-'

0.78

Reviewer

0.68

DragonMagazine

0.67

BCE

0.64

ESV

0.64

 Sakuya

0.63

enhagen

0.62

Guide

0.61

 Robbins

0.60

Activations Density 0.143%

dates or years

specific years mentioned in the text

No Comments

No Known Activations