INDEX

Explanations

instances where the number "Two" is mentioned

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Two."

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

ugu

-0.79

 guiActiveUnfocused

-0.68

rir

-0.67

utable

-0.66

ifice

-0.66

 favour

-0.65

akings

-0.65

Ö

-0.63

olson

-0.62

uffer

-0.62

POSITIVE LOGITS

 thirds

1.35

teen

1.07

een

1.04

 Thousand

1.02

 Hundred

0.99

 Months

0.94

 weeks

0.90

 Weeks

0.89

 Ways

0.84

nd

0.81

Activations Density 0.039%

instances where the number "Two" is mentioned

instances of the word "Two."

No Comments

No Known Activations