INDEX

Explanations

phrases expressing a step-by-step explanation or review

oai_token-act-pair · gpt-3.5-turbo

phrases that involve taking a closer examination or analysis of a subject

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

ald

-0.71

utm

-0.68

iar

-0.67

ley

-0.64

lees

-0.61

 outweigh

-0.61

ONSORED

-0.60

eed

-0.60

leys

-0.59

Always

-0.59

POSITIVE LOGITS

GROUND

0.79

 basics

0.76

 primer

0.76

 briefly

0.75

 hypot

0.74

 specifics

0.74

 empir

0.72

 recap

0.71

 nutshell

0.70

Overview

0.69

Activations Density 0.249%

phrases expressing a step-by-step explanation or review

phrases that involve taking a closer examination or analysis of a subject

No Comments

No Known Activations