INDEX

Explanations

phrases related to leadership or individuals in positions of authority

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "leader."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Neighbor

-0.66

\/\/

-0.64

ascade

-0.63

ITNESS

-0.62

Pwr

-0.61

ALLY

-0.60

agra

-0.59

 Fusion

-0.59

LV

-0.58

 Collider

-0.57

POSITIVE LOGITS

boards

1.37

board

1.26

doms

1.09

pins

0.94

leader

0.93

aroo

0.92

hips

0.90

pin

0.90

esses

0.90

less

0.87

Activations Density 0.067%

phrases related to leadership or individuals in positions of authority

occurrences of the word "leader."

No Comments

No Known Activations