INDEX

Explanations

mentions of the word "hotel"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hot" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 convol

-0.67

anke

-0.67

ISION

-0.66

orrow

-0.66

 Commando

-0.65

 literacy

-0.64

uthor

-0.64

 Fargo

-0.64

 Kinn

-0.63

 Borders

-0.63

POSITIVE LOGITS

hot

0.88

ter

0.82

rop

0.82

assium

0.80

tery

0.79

ographed

0.78

shot

0.77

rod

0.76

eers

0.76

butt

0.76

Activations Density 0.009%

mentions of the word "hotel"

instances of the word "hot" in various contexts

No Comments

No Known Activations