INDEX

Explanations

statistics related to capacity or capability measurements

oai_token-act-pair · gpt-3.5-turbo

references to capacity 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 @ 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

aida

-0.78

roma

-0.78

rom

-0.74

dash

-0.72

uran

-0.72

wealth

-0.70

utorial

-0.68

doms

-0.67

chy

-0.67

generic

-0.66

POSITIVE LOGITS

 capacities

1.26

 capacity

1.21

 utilization

1.03

 Capacity

0.96

capacity

0.84

 mismatch

0.82

auga

0.78

ibilities

0.78

 overflow

0.75

 gaps

0.73

Activations Density 0.015%

statistics related to capacity or capability measurements

references to capacity in various contexts

No Comments

No Known Activations