INDEX

Explanations

phrases related to political or social events

oai_token-act-pair · gpt-3.5-turbo

commas, indicating lists or additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

oir

-0.69

âĶĢâĶĢâĶĢâĶĢ

-0.67

LOCK

-0.65

ãĥ¥

-0.61

IBLE

-0.58

itar

-0.58

itation

-0.56

ente

-0.55

 guid

-0.55

HEAD

-0.54

POSITIVE LOGITS

eatures

0.88

}"

0.81

 denies

0.76

etheless

0.76

 withdrew

0.72

 nevertheless

0.71

 namely

0.70

 albeit

0.70

anwhile

0.68

 remembers

0.68

Activations Density 0.179%

phrases related to political or social events

commas, indicating lists or additional information

No Comments

No Known Activations