INDEX

Explanations

references to the city of Naples (Napoli)

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Nap" or its variations, likely indicating a focus on locations or entities associated with that term

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

the token "Nap" in a proper noun

Explanation Uploaded by User

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Gemini

-0.82

 Carbuncle

-0.70

 Drift

-0.69

 Jimmy

-0.67

 Falk

-0.64

 Founders

-0.62

 Stra

-0.59

 enough

-0.58

 Supplemental

-0.58

RECT

-0.57

POSITIVE LOGITS

oleon

1.62

alm

1.54

olit

1.54

olitan

1.54

olean

1.53

oli

1.26

erville

1.14

kins

1.13

ole

1.08

oca

1.03

Activations Density 0.046%

references to the city of Naples (Napoli)

occurrences of the word "Nap" or its variations, likely indicating a focus on locations or entities associated with that term

the token "Nap" in a proper noun

No Comments

No Known Activations