INDEX

Explanations

names of people or characters

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.75

ModLoader

-0.74

 underwater

-0.73

âĶĢâĶĢ

-0.71

anwhile

-0.69

etheless

-0.68

LEASE

-0.65

 Melania

-0.65

ãĥŁ

-0.64

 Galileo

-0.64

POSITIVE LOGITS

atz

1.02

ovich

1.01

lett

1.00

itz

1.00

acci

0.98

zen

0.97

inger

0.95

inski

0.95

owski

0.93

ansky

0.93

Activations Density 0.306%

names of people or characters

proper nouns, particularly names of individuals

No Comments

No Known Activations