INDEX

Explanations

instances where an action is being given or directed towards something

oai_token-act-pair · gpt-3.5-turbo

phrases that involve giving something attention or consideration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ater

-0.73

nels

-0.73

nel

-0.71

amiya

-0.70

yrinth

-0.70

asses

-0.69

alde

-0.68

ablish

-0.66

BILITIES

-0.64

Ship

-0.63

POSITIVE LOGITS

hum

0.73

 priority

0.71

 goodbye

0.71

 legitimacy

0.68

 airs

0.66

 enthusi

0.65

kell

0.65

 immortality

0.63

 Goodbye

0.63

andom

0.63

Activations Density 0.166%

instances where an action is being given or directed towards something

phrases that involve giving something attention or consideration

No Comments

No Known Activations