INDEX

Explanations

opinion pieces or editorials

oai_token-act-pair · gpt-3.5-turbo

instances of opinion pieces or articles with the term "op-ed."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Beautiful

-0.70

 taxing

-0.68

 Awakens

-0.67

 Illum

-0.63

 EntityItem

-0.63

 GOODMAN

-0.63

 finer

-0.60

 Dign

-0.60

ãĥĨãĤ£

-0.59

 surg

-0.58

POSITIVE LOGITS

comment

0.79

agon

0.79

ansion

0.78

inion

0.77

code

0.77

stroke

0.77

articles

0.77

office

0.77

Ops

0.76

etric

0.75

Activations Density 0.036%

opinion pieces or editorials

instances of opinion pieces or articles with the term "op-ed."

No Comments

No Known Activations