INDEX

Explanations

locations or titles with the word "Mis" in them

oai_token-act-pair · gpt-3.5-turbo

the word "Mis" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Schwarzenegger

-0.74

 Guardians

-0.71

 Gaul

-0.70

 Defenders

-0.65

 Ferr

-0.62

Ing

-0.62

Aur

-0.62

 IMAGES

-0.61

ysis

-0.61

 Resurrection

-0.61

POSITIVE LOGITS

cellaneous

1.40

ogyn

1.39

chief

1.34

fortune

1.29

guided

1.14

leading

1.11

placed

1.09

bah

1.05

beh

1.04

appropri

0.99

Activations Density 0.012%

locations or titles with the word "Mis" in them

the word "Mis" in various contexts

No Comments

No Known Activations