INDEX

Explanations

references to a specific geographical location that includes the term "oga"

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

wolves

-0.67

onym

-0.66

lines

-0.64

 Innocent

-0.64

bul

-0.62

self

-0.61

 newsp

-0.60

 Debor

-0.60

 readable

-0.59

UID

-0.59

POSITIVE LOGITS

oga

1.66

 Springs

1.03

issance

0.84

uga

0.81

veland

0.81

akra

0.79

oche

0.77

arde

0.75

alus

0.73

userc

0.73

Activations Density 0.006%

references to a specific geographical location that includes the term "oga"

references to geographical locations and notable figures

No Comments

No Known Activations