INDEX

Explanations

proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

key entities, particularly in academic or historical 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

icient

-0.57

isSpecialOrderable

-0.55

inki

-0.55

kefeller

-0.53

etsy

-0.53

 teasp

-0.50

sylv

-0.49

cest

-0.49

catentry

-0.49

ãĥĩãĤ£

-0.48

POSITIVE LOGITS

Jr

0.61

ulhu

0.58

ĪĴ

0.56

 Method

0.53

 Pattern

0.51

Ass

0.51

ALLY

0.50

lang

0.50

vez

0.48

abbage

0.46

Activations Density 1.362%

proper nouns or specific names

key entities, particularly in academic or historical contexts

No Comments

No Known Activations