INDEX

Explanations

words related to repairing and reusing objects or systems

oai_token-act-pair · gpt-3.5-turbo

words related to restrictions, reprocessing, and reevaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

NESS

-0.80

 confessions

-0.66

 divergence

-0.64

 beliefs

-0.64

 sincerity

-0.64

 sake

-0.63

 nutshell

-0.61

 seriousness

-0.61

lihood

-0.61

 stability

-0.60

POSITIVE LOGITS

rolled

1.33

idered

1.32

eded

1.30

ased

1.30

ised

1.29

idden

1.29

urated

1.29

itored

1.29

aded

1.26

arthed

1.24

Activations Density 0.247%

words related to repairing and reusing objects or systems

words related to restrictions, reprocessing, and reevaluation

No Comments

No Known Activations