INDEX

Explanations

phrases indicating nearly the same or very similar items, circumstances, or actions

oai_token-act-pair · gpt-3.5-turbo

phrases and words emphasizing frequency or recurrence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Louie

-0.84

 Kirby

-0.65

 Bard

-0.64

Ki

-0.62

 Colors

-0.62

andise

-0.58

gio

-0.57

 Blend

-0.57

 Jord

-0.57

":["

-0.56

POSITIVE LOGITS

rontal

0.73

lyak

0.72

èª

0.71

osher

0.68

haust

0.66

 spoiler

0.65

ï¸

0.65

maxwell

0.64

Ö

0.64

Ïī

0.63

Activations Density 0.188%

phrases indicating nearly the same or very similar items, circumstances, or actions

phrases and words emphasizing frequency or recurrence

No Comments

No Known Activations