INDEX

Explanations

proper nouns related to different locations or entities

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

STON

-0.71

 palpable

-0.66

UST

-0.64

INS

-0.63

usc

-0.62

 imprisonment

-0.62

lez

-0.61

arantine

-0.60

 restraint

-0.60

 quantitative

-0.59

POSITIVE LOGITS

aters

1.09

untled

0.92

hip

0.91

ucker

0.88

etter

0.86

ervatives

0.86

acers

0.86

 Royale

0.86

chool

0.85

aimon

0.82

Activations Density 0.016%

proper nouns related to different locations or entities

No Comments

No Known Activations