INDEX

Explanations

specific phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

quotation marks and phrases enclosed within them

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

 Alger

-0.70

 Nieto

-0.69

 Azerb

-0.68

 Choi

-0.67

 viewers

-0.65

 Gaal

-0.64

 describ

-0.64

 photographers

-0.64

 upon

-0.64

 Rica

-0.63

POSITIVE LOGITS

classic

1.29

little

1.17

most

1.14

ordinary

1.08

official

1.06

technical

1.06

real

1.04

true

1.03

perfect

1.03

personal

1.03

Activations Density 0.068%

specific phrases enclosed in quotation marks

quotation marks and phrases enclosed within them

No Comments

No Known Activations