INDEX

Explanations

mentions of "The Washington Post"

oai_token-act-pair · gpt-3.5-turbo

references to specific newspapers or media outlets, particularly "The Washington Post."

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

gone

-0.76

 bragging

-0.72

sed

-0.70

sbm

-0.66

 disadvant

-0.63

stood

-0.63

 Canaveral

-0.61

 fasc

-0.61

 directions

-0.60

 Emin

-0.59

POSITIVE LOGITS

 Writer

0.81

 Writers

0.80

 Staff

0.72

 NETWORK

0.71

pei

0.70

Buy

0.68

 Wire

0.67

ipeg

0.67

 Newsp

0.66

 reporter

0.66

Activations Density 0.102%

mentions of "The Washington Post"

references to specific newspapers or media outlets, particularly "The Washington Post."

No Comments

No Known Activations