INDEX

Explanations

phrases related to public policies and activities

oai_token-act-pair · gpt-3.5-turbo

terms related to public safety and engagement initiatives

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

IFrame

Link

•Words that rhyme with flat

new

No Comments

Negative Logits

 Ruff

-0.71

 Clyde

-0.69

 Ragnarok

-0.67

eters

-0.67

 sunset

-0.66

 Bolt

-0.64

 Odyssey

-0.62

 Orion

-0.62

è£ħ

-0.61

 Christensen

-0.61

POSITIVE LOGITS

favorite

0.98

service

0.96

relations

0.89

produced

0.88

order

0.88

eye

0.87

generated

0.87

sector

0.87

purpose

0.86

facing

0.86

Activations Density 0.090%

phrases related to public policies and activities

terms related to public safety and engagement initiatives

No Comments

No Known Activations