INDEX

Explanations

instances where the number "two" is mentioned

oai_token-act-pair · gpt-3.5-turbo

references to quantities or pairings of items

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

assisted

-0.75

buster

-0.74

enment

-0.72

ãĤ´ãĥ³

-0.71

icip

-0.70

ufact

-0.67

©¶æ

-0.66

[|

-0.66

ÃĥÃĤ

-0.66

GoldMagikarp

-0.64

POSITIVE LOGITS

 reasons

0.87

 reason

0.84

 shortage

0.79

 distinct

0.74

 chance

0.74

 similarities

0.72

 aster

0.67

WAY

0.67

 ways

0.67

 overlap

0.66

Activations Density 0.080%

instances where the number "two" is mentioned

references to quantities or pairings of items

No Comments

No Known Activations