INDEX

Explanations

names starting with 'He'

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of a specific person or character's name, primarily "He" or "She"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

etheless

-0.77

quo

-0.62

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.62

 haul

-0.61

ãĥ¼ãĥĨ

-0.59

 bombard

-0.59

anwhile

-0.59

 Cummings

-0.57

 eleph

-0.57

 Thoughts

-0.56

POSITIVE LOGITS

arer

1.10

lder

1.04

arers

0.96

ALTH

0.88

resy

0.87

isman

0.87

isen

0.86

ppard

0.86

iden

0.85

yd

0.85

Activations Density 0.050%

names starting with 'He'

repeated mentions of a specific person or character's name, primarily "He" or "She"

No Comments

No Known Activations