INDEX

Explanations

phrases related to sections of text signifying examples or subsets

oai_token-act-pair · gpt-3.5-turbo

the repeated occurrence of the word "Some."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

enance

-0.75

SPONSORED

-0.74

abilities

-0.69

itude

-0.69

vest

-0.67

 borne

-0.67

âĹ¼

-0.65

ades

-0.64

itten

-0.63

raid

-0.62

POSITIVE LOGITS

body

1.04

how

1.01

place

0.96

ones

0.85

ESA

0.73

ONE

0.71

 consolation

0.70

HOW

0.69

 notable

0.66

 semblance

0.64

Activations Density 0.096%

phrases related to sections of text signifying examples or subsets

the repeated occurrence of the word "Some."

No Comments

No Known Activations