INDEX

Explanations

words related to political figures and events

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

DragonMagazine

-0.92

estamp

-0.90

 fucked

-0.70

============

-0.69

retty

-0.68

emort

-0.65

!--

-0.65

 GOODMAN

-0.64

furt

-0.64

STD

-0.64

POSITIVE LOGITS

vous

0.67

 Gael

0.62

de

0.61

deen

0.61

 Labrador

0.61

Ã¡

0.60

 Trou

0.60

Lago

0.60

 Gamble

0.60

aga

0.58

Activations Density 0.288%

words related to political figures and events

references to specific locations or establishments

No Comments

No Known Activations