INDEX

Explanations

verbs that indicate preferences or actions related to personal hobbies or habits

oai_token-act-pair · gpt-3.5-turbo

phrases that express actions prefaced by "to"

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

 Settlement

-0.65

ratulations

-0.65

 clearance

-0.61

era

-0.60

river

-0.60

inguished

-0.59

 Everest

-0.58

 sterling

-0.58

 Nationwide

-0.58

 yielded

-0.58

POSITIVE LOGITS

 speculate

1.10

 remind

1.07

 pretend

1.02

 tease

1.01

 think

1.01

 hear

0.99

 visualize

0.97

 imagine

0.97

 joke

0.95

see

0.94

Activations Density 0.052%

verbs that indicate preferences or actions related to personal hobbies or habits

phrases that express actions prefaced by "to"

No Comments

No Known Activations