INDEX

Explanations

words related to leadership roles

oai_token-act-pair · gpt-3.5-turbo

references to leadership roles or positions of authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 mell

-0.70

PsyNetMessage

-0.69

 resil

-0.68

Suc

-0.66

Constructed

-0.64

 Strat

-0.64

 Sons

-0.63

Avg

-0.62

Mub

-0.61

ickr

-0.61

POSITIVE LOGITS

canon

1.05

butt

1.03

quarter

1.01

gear

1.00

liner

1.00

lining

0.98

scar

0.93

ache

0.92

phones

0.92

heading

0.92

Activations Density 0.029%

words related to leadership roles

references to leadership roles or positions of authority

No Comments

No Known Activations