INDEX

Explanations

phrases related to promotions or offers

oai_token-act-pair · gpt-3.5-turbo

mentions of the New York Times and its related services

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

pmwiki

-0.66

 Classification

-0.64

DOS

-0.62

 Corpor

-0.60

Footnote

-0.60

 Warrant

-0.59

 perm

-0.59

 theoret

-0.58

 alias

-0.58

urized

-0.58

POSITIVE LOGITS

interstitial

0.74

entimes

0.67

idays

0.67

erity

0.65

 Literary

0.64

leans

0.64

Ble

0.62

imentary

0.62

isure

0.62

NPR

0.61

Activations Density 0.044%

phrases related to promotions or offers

mentions of the New York Times and its related services

No Comments

No Known Activations