INDEX

Explanations

technical terms and instructions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating descriptions or explanations of topics

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

WT

-0.74

 Allies

-0.71

Hon

-0.68

icum

-0.66

)</

-0.65

esters

-0.65

 Gamble

-0.64

LC

-0.64

Bridge

-0.62

Jar

-0.61

POSITIVE LOGITS

how

0.90

 topics

0.89

why

0.85

 aspects

0.82

 similarities

0.81

 basics

0.77

 excerpts

0.77

WHY

0.77

 trends

0.75

 feasibility

0.71

Activations Density 0.232%

technical terms and instructions

phrases indicating descriptions or explanations of topics

No Comments

No Known Activations