INDEX

Explanations

advertisements within content

oai_token-act-pair · gpt-3.5-turbo

instances of advertisements in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stood

-0.67

ties

-0.66

clus

-0.63

fulness

-0.62

ãĥ´

-0.61

 wound

-0.61

mate

-0.61

 perspect

-0.60

 omission

-0.60

 accessibility

-0.59

POSITIVE LOGITS

 Continue

0.93

 Advertisement

0.91

advertisement

0.84

Credit

0.75

Advertisement

0.74

Skip

0.71

usercontent

0.70

 COURT

0.68

credit

0.68

sburg

0.66

Activations Density 0.021%

advertisements within content

instances of advertisements in the text

No Comments

No Known Activations