INDEX

Explanations

instances of the word "Jackson"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jackson."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ancial

-0.81

jad

-0.77

ĻĤ

-0.76

VOL

-0.73

xit

-0.73

available

-0.72

spread

-0.72

lator

-0.72

evil

-0.71

requ

-0.70

POSITIVE LOGITS

 Hole

0.95

SON

0.84

 Jackson

0.80

 Browne

0.79

ston

0.78

angel

0.73

hurst

0.69

 Heights

0.69

inson

0.68

hoe

0.67

Activations Density 0.009%

instances of the word "Jackson"

mentions of the name "Jackson."

No Comments

No Known Activations