INDEX

Explanations

phrases related to difficulty or challenge

oai_token-act-pair · gpt-3.5-turbo

phrases describing difficulty or challenges

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

uador

-0.71

allery

-0.70

umbn

-0.69

atern

-0.68

ournal

-0.67

uality

-0.65

ocument

-0.65

ript

-0.64

gdala

-0.62

 Siem

-0.60

POSITIVE LOGITS

coded

1.23

wired

1.14

working

1.10

ball

0.95

core

0.92

ening

0.90

BALL

0.87

hitting

0.86

ened

0.83

fork

0.81

Activations Density 0.032%

phrases related to difficulty or challenge

phrases describing difficulty or challenges

No Comments

No Known Activations