INDEX

Explanations

words related to balance or equilibrium

oai_token-act-pair · gpt-3.5-turbo

terms related to load balancing and its 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

ENTION

-0.73

ICLE

-0.72

naire

-0.70

Page

-0.70

 Legacy

-0.69

ALK

-0.69

Construct

-0.68

REE

-0.68

 plural

-0.68

 Halls

-0.68

POSITIVE LOGITS

anches

0.94

ancers

0.86

bal

0.86

anca

0.82

onies

0.80

unker

0.79

ancer

0.79

atable

0.78

ayers

0.78

zers

0.78

Activations Density 0.004%

words related to balance or equilibrium

terms related to load balancing and its various contexts

No Comments

No Known Activations