INDEX

Explanations

keywords indicating transition or continuation to a new point in a discussion

oai_token-act-pair · gpt-3.5-turbo

the sentence starter "Well" indicating conversational responses or transitions

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

âĹ¼

-0.75

illary

-0.69

unal

-0.65

MX

-0.62

rift

-0.62

vg

-0.61

tab

-0.61

machine

-0.60

 booth

-0.60

İĭ

-0.59

POSITIVE LOGITS

esley

1.03

come

0.91

ington

0.85

spring

0.76

espie

0.74

 Cancel

0.71

adays

0.71

Coin

0.68

 hello

0.68

terday

0.67

Activations Density 0.019%

keywords indicating transition or continuation to a new point in a discussion

the sentence starter "Well" indicating conversational responses or transitions

No Comments

No Known Activations