INDEX

Explanations

phrases indicating human verification to check for bots

oai_token-act-pair · gpt-3.5-turbo

phrases related to verification or validation

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

},{"

-0.74

OVER

-0.70

pmwiki

-0.69

 notwithstanding

-0.68

forth

-0.67

CHAPTER

-0.65

overs

-0.64

sheets

-0.64

 showc

-0.63

blow

-0.62

POSITIVE LOGITS

 robot

0.62

 spam

0.59

 resident

0.59

 subscriber

0.58

anooga

0.57

inged

0.57

 Submit

0.56

 Pradesh

0.56

ãĥĦ

0.53

 kidding

0.52

Activations Density 0.030%

phrases indicating human verification to check for bots

phrases related to verification or validation

No Comments

No Known Activations