INDEX

Explanations

proper nouns related to specific locations, organizations, and individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Vulcan

-0.71

estinal

-0.69

tails

-0.66

matic

-0.66

 Africans

-0.65

 fishes

-0.64

 Grail

-0.63

 Viking

-0.63

aredevil

-0.62

 iodine

-0.62

POSITIVE LOGITS

 Bernardino

0.86

_>

0.84

zai

0.80

REDACTED

0.80

cade

0.78

olid

0.78

olic

0.77

ombies

0.76

icio

0.75

icans

0.75

Activations Density 0.026%

proper nouns related to specific locations, organizations, and individuals

proper nouns related to specific locations and names

No Comments

No Known Activations