INDEX

Explanations

names related to Kathleen

oai_token-act-pair · gpt-3.5-turbo

names of political figures, particularly Kathleen and related mentions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icult

-0.88

unin

-0.83

 eleph

-0.81

ured

-0.80

raltar

-0.80

gers

-0.79

ierrez

-0.77

alls

-0.76

erred

-0.76

urity

-0.76

POSITIVE LOGITS

 Wynne

1.00

 Yamato

0.94

 Kathleen

0.85

 Rousse

0.80

 Upton

0.76

 McCarthy

0.76

 Snyder

0.75

Wen

0.72

 Marie

0.72

 Hanna

0.72

Activations Density 0.019%

names related to Kathleen

names of political figures, particularly Kathleen and related mentions

No Comments

No Known Activations