INDEX

Explanations

words or phrases related to specific names or locations

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or entities involved in significant events or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

anova

-0.73

REL

-0.71

bg

-0.63

 ingred

-0.63

xus

-0.62

wat

-0.60

Ingredients

-0.59

 heaviest

-0.59

DAQ

-0.59

 kittens

-0.59

POSITIVE LOGITS

hower

0.81

vironment

0.80

tainment

0.76

 Predator

0.76

ascript

0.73

anasia

0.70

ilon

0.70

ionage

0.70

 Proxy

0.68

Activations Density 0.102%

words or phrases related to specific names or locations

references to specific individuals or entities involved in significant events or roles

No Comments

No Known Activations