INDEX

Explanations

the name "Ken" with various associated words and topics

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "ken" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

accompan

-0.75

 skelet

-0.69

cules

-0.68

 pestic

-0.68

 murd

-0.67

 cryst

-0.67

orers

-0.67

ENCY

-0.65

Þ

-0.65

 eleph

-0.64

POSITIVE LOGITS

wald

1.06

azi

1.03

ners

1.00

vironment

1.00

hof

0.98

feld

0.98

ken

0.94

heit

0.94

ning

0.93

burgh

0.89

Activations Density 0.025%

the name "Ken" with various associated words and topics

mentions of the word "ken" in various contexts

No Comments

No Known Activations