INDEX

Explanations

verbs that involve giving instructions or commands to someone

oai_token-act-pair · gpt-3.5-turbo

commands or directives

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

 Appears

-0.82

quickShipAvailable

-0.73

 threaded

-0.67

 proven

-0.66

 persuasive

-0.60

 seams

-0.59

uded

-0.58

 testim

-0.58

 intrig

-0.58

 evid

-0.58

POSITIVE LOGITS

 beware

1.12

 evacuate

1.00

 avoid

0.96

 obey

0.95

 prepare

0.94

 keep

0.94

 proceed

0.93

 refrain

0.93

 prioritize

0.91

 stop

0.91

Activations Density 0.114%

verbs that involve giving instructions or commands to someone

commands or directives

No Comments

No Known Activations