INDEX

Explanations

phrases indicating a process or activity that has been ongoing or completed

oai_token-act-pair · gpt-3.5-turbo

expressions related to processes or situations that are ongoing or in development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

obal

-0.80

 Flavoring

-0.67

ospons

-0.65

lav

-0.64

asar

-0.63

imar

-0.63

icipated

-0.61

amar

-0.59

ensions

-0.59

ush

-0.58

POSITIVE LOGITS

 psychiat

0.63

 psychopath

0.60

FontSize

0.58

 understatement

0.58

 leash

0.58

 announcer

0.57

 applause

0.57

WHERE

0.56

bos

0.56

beh

0.55

Activations Density 0.844%

phrases indicating a process or activity that has been ongoing or completed

expressions related to processes or situations that are ongoing or in development

No Comments

No Known Activations