INDEX

Explanations

proper nouns, particularly related to locations and people's names

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific locations or entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rac

-0.84

opian

-0.74

bishop

-0.74

iris

-0.73

 diving

-0.72

camp

-0.72

zag

-0.72

college

-0.71

amic

-0.71

 bladder

-0.71

POSITIVE LOGITS

 Less

1.26

 Given

1.23

 Enough

1.23

 Remove

1.23

 Where

1.22

 Needs

1.21

 Absent

1.21

 Only

1.21

Not

1.20

Put

1.18

Activations Density 0.368%

proper nouns, particularly related to locations and people's names

proper nouns and specific locations or entities

No Comments

No Known Activations