INDEX

Explanations

prepositions

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "in"

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

 plurality

-0.78

 stumble

-0.74

ropolitan

-0.74

Ħ¢

-0.72

 flaw

-0.69

astery

-0.69

 aber

-0.69

SPONSORED

-0.68

eele

-0.68

 laps

-0.68

POSITIVE LOGITS

pet

0.81

beard

0.80

vous

0.80

ayers

0.77

tips

0.71

anger

0.69

iki

0.69

giving

0.69

mast

0.68

venge

0.67

Activations Density 0.000%

prepositions

the presence of the word "in"

No Comments

No Known Activations