INDEX

Explanations

phrases related to political discussions and agreements

oai_token-act-pair · gpt-3.5-turbo

statements related to predictions about the future

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 markings

-0.73

 sibling

-0.69

Custom

-0.68

 contracted

-0.68

 CLSID

-0.67

 handles

-0.66

 initials

-0.66

 booking

-0.65

 visitation

-0.64

 placement

-0.64

POSITIVE LOGITS

 Keynes

1.21

 Chomsky

1.21

 Krugman

1.16

 Libertarian

1.14

 economists

1.11

 Economist

1.11

 populism

1.10

 libertarians

1.09

omsky

1.09

 libertarian

1.09

Activations Density 1.128%

phrases related to political discussions and agreements

statements related to predictions about the future

No Comments

No Known Activations