INDEX

Explanations

instances of physical actions involving force or conflict

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "get" and its variations, indicating action or occurrence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

worthiness

-0.68

velt

-0.65

 endeavour

-0.58

keeping

-0.58

 Archdemon

-0.58

 entirety

-0.57

haus

-0.57

 Implementation

-0.57

NESS

-0.55

semb

-0.55

POSITIVE LOGITS

rid

1.16

 bored

1.02

 acquainted

1.01

 stuck

0.99

 bitten

0.97

 drunk

0.96

 married

0.96

 distracted

0.93

 lucky

0.93

 addicted

0.93

Activations Density 0.111%

instances of physical actions involving force or conflict

instances of the verb "get" and its variations, indicating action or occurrence

No Comments

No Known Activations