INDEX

Explanations

phrases related to the term "Ninja"

oai_token-act-pair · gpt-3.5-turbo

references to "Nin" or "ninja" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mileage

-0.72

inventoryQuantity

-0.71

igating

-0.69

 fault

-0.67

 Miranda

-0.66

INGS

-0.65

 PRESS

-0.65

HIP

-0.64

ansas

-0.64

 Incarn

-0.61

POSITIVE LOGITS

eteen

1.72

eteenth

1.65

eties

1.39

jas

1.36

ety

1.25

ormal

1.09

ovember

1.01

ja

0.99

jah

0.98

umbered

0.95

Activations Density 0.008%

phrases related to the term "Ninja"

references to "Nin" or "ninja" in various contexts

No Comments

No Known Activations