INDEX

Explanations

names ending in 'bert'

oai_token-act-pair · gpt-3.5-turbo

the repetition of the name "Bert" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

esthetic

-0.78

heed

-0.74

ntil

-0.72

phis

-0.70

IFT

-0.69

olved

-0.68

istor

-0.65

oter

-0.65

stream

-0.65

phan

-0.64

POSITIVE LOGITS

atoes

0.86

stadt

0.79

 Hoover

0.78

 Ames

0.76

 Blumenthal

0.75

stown

0.73

rics

0.73

sson

0.72

furt

0.71

aum

0.70

Activations Density 0.019%

names ending in 'bert'

the repetition of the name "Bert" in various contexts

No Comments

No Known Activations