INDEX

Explanations

phrases related to spatial locations or directions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the" at various points in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

eers

-0.72

aris

-0.71

paio

-0.69

intosh

-0.67

 firsthand

-0.65

Wik

-0.65

LY

-0.65

uba

-0.64

arians

-0.63

maid

-0.62

POSITIVE LOGITS

 country

0.88

 proverbial

0.85

 equation

0.84

 millennium

0.83

 smallest

0.81

 latter

0.80

 world

0.80

 aforementioned

0.80

 spectrum

0.77

 circle

0.77

Activations Density 0.257%

phrases related to spatial locations or directions

instances of the word "the" at various points in the text

No Comments

No Known Activations