INDEX

Explanations

names of individuals, including political figures

oai_token-act-pair · gpt-3.5-turbo

phrases that imply time or temporal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 sisters

-0.84

 girls

-0.77

 sister

-0.76

 femin

-0.76

cca

-0.73

 women

-0.72

ona

-0.72

 nuns

-0.71

wcs

-0.68

 females

-0.68

POSITIVE LOGITS

Mr

1.20

His

1.15

He

1.09

Mr

1.09

 Manziel

1.02

He

1.01

iannopoulos

0.95

HAEL

0.93

he

0.92

His

0.92

Activations Density 1.130%

names of individuals, including political figures

phrases that imply time or temporal references

No Comments

No Known Activations