INDEX

Explanations

verbs related to taking action

oai_token-act-pair · gpt-3.5-turbo

action verbs indicating significant activities or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

fur

-0.78

BUR

-0.78

Press

-0.68

mas

-0.68

Impro

-0.66

con

-0.66

quart

-0.65

hon

-0.64

ichi

-0.64

rehens

-0.64

POSITIVE LOGITS

 theirs

0.94

 hers

0.78

 yours

0.78

 anything

0.71

 everything

0.70

 them

0.69

 anyway

0.68

him

0.67

 lots

0.66

 another

0.65

Activations Density 0.624%

verbs related to taking action

action verbs indicating significant activities or decisions

No Comments

No Known Activations