INDEX

Explanations

names containing the pattern "bert"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Hebert."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ntil

-0.76

IFT

-0.70

uncture

-0.69

esthetic

-0.65

BOOK

-0.64

pocket

-0.64

voy

-0.62

heed

-0.61

EMS

-0.60

drawn

-0.58

POSITIVE LOGITS

bert

1.01

atoes

0.96

stadt

0.89

ards

0.88

gomery

0.85

sson

0.82

aum

0.79

ļéĨĴ

0.78

furt

0.78

wald

0.77

Activations Density 0.007%

names containing the pattern "bert"

mentions of the name "Hebert."

No Comments

No Known Activations