INDEX

Explanations

phrases related to the term "Hol" with varying activation levels

oai_token-act-pair · gpt-3.5-turbo

references to a specific entity or name that starts with "Hol."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

EED

-0.73

REE

-0.69

URI

-0.68

ITAL

-0.64

aeda

-0.63

Pool

-0.63

çĶ°

-0.62

 unauthorized

-0.61

 Lowell

-0.60

kick

-0.59

POSITIVE LOGITS

ocaust

1.41

iday

1.37

idays

1.35

ocene

1.22

oho

1.03

inar

1.01

mes

1.00

stery

1.00

isky

0.97

sters

0.95

Activations Density 0.029%

phrases related to the term "Hol" with varying activation levels

references to a specific entity or name that starts with "Hol."

No Comments

No Known Activations