INDEX

Explanations

words related to physical location or presence

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "here."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

catentry

-0.72

paralle

-0.70

cig

-0.67

Wallet

-0.65

Function

-0.65

Health

-0.65

Mail

-0.63

Meat

-0.63

aml

-0.61

Du

-0.60

POSITIVE LOGITS

tics

1.39

tical

1.38

tic

1.21

abouts

1.15

 illegally

0.75

 assembled

0.72

 shores

0.64

 describ

0.64

 tonight

0.63

ground

0.63

Activations Density 0.041%

words related to physical location or presence

occurrences of the word "here."

No Comments

No Known Activations