INDEX

Explanations

names and references to the name "Good"

oai_token-act-pair · gpt-3.5-turbo

the word 'Good' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

âĹ¼

-1.09

ptin

-0.74

RAW

-0.74

oths

-0.73

udic

-0.72

eters

-0.72

ople

-0.71

EStream

-0.70

 concoct

-0.67

pent

-0.67

POSITIVE LOGITS

enough

1.13

bye

1.07

reads

1.02

 Enough

0.97

ness

0.89

 Luck

0.87

 Samar

0.87

sword

0.87

good

0.85

bye

0.85

Activations Density 0.029%

names and references to the name "Good"

the word 'Good' in various contexts

No Comments

No Known Activations