INDEX

Explanations

abbreviations starting with the letter 'V'

oai_token-act-pair · gpt-3.5-turbo

references to a specific entity or brand represented by 'V'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ģĸ

-0.70

Â¯Â¯

-0.65

ãĤ´ãĥ³

-0.63

 deduction

-0.62

Â¯Â¯Â¯Â¯

-0.61

 unrestricted

-0.60

 takedown

-0.59

AAA

-0.59

 writ

-0.59

names

-0.58

POSITIVE LOGITS

oodoo

1.41

ulture

1.34

arsity

1.32

odka

1.28

isions

1.26

antage

1.26

icious

1.22

ampires

1.20

ulnerability

1.20

ISION

1.20

Activations Density 0.028%

abbreviations starting with the letter 'V'

references to a specific entity or brand represented by 'V'

No Comments

No Known Activations