INDEX

Explanations

phrases expressing introspection and contemplation

oai_token-act-pair · gpt-3.5-turbo

references to decision-making processes and discussions about future actions

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

 Accessed

-0.76

Introduced

-0.74

sbm

-0.72

illegal

-0.72

bsite

-0.70

<?

-0.70

\-

-0.70

obile

-0.69

 advertised

-0.68

vernight

-0.67

POSITIVE LOGITS

 ourselves

1.46

 anew

1.15

 oneself

1.10

 wiser

1.03

 sanity

1.01

 yourselves

1.01

 lessons

0.96

 humility

0.89

 truths

0.88

 hopefully

0.85

Activations Density 0.810%

phrases expressing introspection and contemplation

references to decision-making processes and discussions about future actions

No Comments

No Known Activations