INDEX

Explanations

names of people or characters, particularly surnames

oai_token-act-pair · gpt-3.5-turbo

prominent names associated with significant events or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ModLoader

-0.74

etheless

-0.54

 FANTASY

-0.52

âĶĢâĶĢ

-0.48

 apex

-0.48

 cryst

-0.47

duino

-0.45

 polar

-0.44

 symbolism

-0.44

 idols

-0.43

POSITIVE LOGITS

zinski

0.70

inski

0.63

itz

0.62

haus

0.61

mann

0.61

itte

0.61

wine

0.60

orst

0.60

zynski

0.60

zen

0.59

Activations Density 0.877%

names of people or characters, particularly surnames

prominent names associated with significant events or positions

No Comments

No Known Activations