INDEX

Explanations

phrases indicating a similarity or comparison

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing frequency or repetition

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Louie

-0.80

 Kirby

-0.59

 behav

-0.58

gio

-0.57

mons

-0.57

olor

-0.57

 Bard

-0.55

 Regions

-0.55

 Galile

-0.55

 wisely

-0.55

POSITIVE LOGITS

rontal

0.69

aneously

0.68

èª

0.67

ties

0.66

istic

0.66

itals

0.64

RANT

0.64

RS

0.64

osher

0.63

maxwell

0.62

Activations Density 0.135%

phrases indicating a similarity or comparison

phrases emphasizing frequency or repetition

No Comments

No Known Activations