INDEX

Explanations

keywords related to exhibitions or events

oai_token-act-pair · gpt-3.5-turbo

mentions of expos and exhibitions

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

croft

-0.78

gettable

-0.78

radical

-0.76

bole

-0.72

balanced

-0.71

tie

-0.71

tymology

-0.67

 precarious

-0.67

alias

-0.65

ties

-0.65

POSITIVE LOGITS

 Expo

1.21

 Convention

1.00

ption

0.88

 Attend

0.80

 Exhibition

0.77

Fest

0.76

eport

0.74

 Booth

0.71

 Jinping

0.71

 Sessions

0.71

Activations Density 0.007%

keywords related to exhibitions or events

mentions of expos and exhibitions

No Comments

No Known Activations