INDEX

Explanations

prefixes "pre-"

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "pre-" relating to preparation or pre-existing conditions

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

Ago

-0.62

 sidelines

-0.61

 Ukrain

-0.59

Rex

-0.58

IBLE

-0.58

 misunderstood

-0.57

 rooting

-0.56

 whis

-0.55

 loophole

-0.55

 Trend

-0.54

POSITIVE LOGITS

fecture

1.40

requisites

1.35

achers

1.32

lude

1.32

occup

1.31

occupied

1.24

cludes

1.22

emption

1.20

fect

1.20

cession

1.17

Activations Density 0.020%

prefixes "pre-"

instances of the prefix "pre-" relating to preparation or pre-existing conditions

No Comments

No Known Activations