INDEX

Explanations

terms related to legal or formal processes and actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal actions and their consequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

edia

-0.61

verse

-0.58

 Saying

-0.57

 ILCS

-0.57

 detrim

-0.55

cise

-0.54

SAY

-0.54

merce

-0.53

 Yourself

-0.53

 forgetting

-0.52

POSITIVE LOGITS

 ensued

1.59

 exists

1.51

 emerged

1.51

 occurred

1.46

 existed

1.45

 emerges

1.44

 arose

1.38

 awaited

1.35

 arises

1.34

 prevailed

1.33

Activations Density 0.562%

terms related to legal or formal processes and actions

phrases related to legal actions and their consequences

No Comments

No Known Activations