INDEX

Explanations

locations and places related to the United States

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations or specific places

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

ensable

-0.61

kefeller

-0.60

apego

-0.59

 fitt

-0.58

————

-0.57

heid

-0.57

Appearances

-0.56

milo

-0.56

ĪĴ

-0.56

ppard

-0.55

POSITIVE LOGITS

 circles

0.67

 classrooms

0.64

 coffers

0.62

 periphery

0.61

 where

0.60

 realm

0.60

 contexts

0.59

 corners

0.59

 districts

0.58

':

0.58

Activations Density 0.764%

locations and places related to the United States

references to geographical locations or specific places

No Comments

No Known Activations