INDEX

Explanations

names of people, places, and organizations

oai_token-act-pair · gpt-3.5-turbo

certain names and terms related to leadership or authority figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Dise

-0.66

ement

-0.64

 inval

-0.63

 Seraph

-0.61

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.60

 Helpful

-0.60

ãĥ¼ãĥĨ

-0.59

riott

-0.56

soever

-0.54

 Gleaming

-0.54

POSITIVE LOGITS

yz

0.71

ĵĺ

0.66

alid

0.63

uild

0.61

ensibly

0.59

orb

0.56

ovsky

0.56

masters

0.56

hid

0.54

Î»

0.54

Activations Density 0.306%

names of people, places, and organizations

certain names and terms related to leadership or authority figures

No Comments

No Known Activations