INDEX

Explanations

names or terms related to specific individuals

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those with the name "Nad."

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

ãĥĩãĤ£

-0.70

âĸ¬

-0.67

EED

-0.67

FTWARE

-0.66

por

-0.65

 Izan

-0.64

hazard

-0.63

tenance

-0.63

 beans

-0.63

 Beans

-0.62

POSITIVE LOGITS

abase

0.86

atron

0.84

ifiers

0.83

icate

0.82

adr

0.82

ifications

0.81

senal

0.80

uds

0.80

acons

0.78

ars

0.78

Activations Density 0.025%

names or terms related to specific individuals

references to specific individuals, particularly those with the name "Nad."

No Comments

No Known Activations