INDEX

Explanations

references to political figures and statements

oai_token-act-pair · gpt-3.5-turbo

references to public figures and their statements or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Craigslist

-0.81

 Manson

-0.72

atown

-0.71

 Buddy

-0.69

 disenfranch

-0.68

Kids

-0.68

 Bigfoot

-0.68

 predators

-0.67

 Pryor

-0.67

 Appalach

-0.67

POSITIVE LOGITS

 Lavrov

1.33

plom

1.19

 diplomatic

1.19

 envoy

1.17

 Rouhani

1.14

anyahu

1.14

 Nato

1.10

 ministerial

1.08

 bilateral

1.08

 Foreign

1.07

Activations Density 0.940%

references to political figures and statements

references to public figures and their statements or actions

No Comments

No Known Activations