INDEX

Explanations

phrases related to future events or outcomes

oai_token-act-pair · gpt-3.5-turbo

references to anticipated or future outcomes

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

toe

-0.75

emen

-0.74

manship

-0.74

lua

-0.73

books

-0.70

mans

-0.70

men

-0.70

erie

-0.68

gun

-0.68

rooms

-0.67

POSITIVE LOGITS

ity

1.05

ities

1.05

ITY

0.94

 demise

0.87

 downfall

0.86

aneously

0.85

ITIES

0.81

itous

0.80

 occupant

0.76

 successor

0.76

Activations Density 0.011%

phrases related to future events or outcomes

references to anticipated or future outcomes

No Comments

No Known Activations