INDEX

Explanations

references to the news network FOX

oai_token-act-pair · gpt-3.5-turbo

references to the FOX news network

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Pg

-0.69

Ach

-0.68

Sov

-0.64

ctor

-0.64

Stack

-0.63

 unres

-0.63

Acknowled

-0.62

 subsistence

-0.62

 immersion

-0.62

ococ

-0.61

POSITIVE LOGITS

FOX

3.79

FOX

2.83

Fox

1.83

Fox

1.80

CBS

1.57

NBC

1.50

ABC

1.37

CBS

1.34

NBC

1.33

fox

1.28

Activations Density 0.016%

references to the news network FOX

references to the FOX news network

No Comments

No Known Activations