INDEX

Explanations

words indicating actions done with intent or purpose

oai_token-act-pair · gpt-3.5-turbo

terms related to intentional or deliberate actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rite

-0.85

busters

-0.69

 HERO

-0.67

 ANGEL

-0.67

 Warriors

-0.66

 Tycoon

-0.65

Rated

-0.63

iry

-0.63

 Colleges

-0.62

 Emir

-0.62

POSITIVE LOGITS

 deliberately

1.05

 intentionally

0.96

 planted

0.92

 purposely

0.90

 purposefully

0.85

 reprodu

0.82

 plotted

0.82

 disreg

0.80

 indul

0.77

 misrepresent

0.77

Activations Density 0.009%

words indicating actions done with intent or purpose

terms related to intentional or deliberate actions

No Comments

No Known Activations