INDEX

Explanations

names related to Jon

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jon"

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

holders

-0.79

doors

-0.69

flies

-0.67

ledged

-0.66

grades

-0.66

graduate

-0.66

OTUS

-0.65

milo

-0.64

bearing

-0.64

sided

-0.63

POSITIVE LOGITS

athon

1.17

Ben

0.99

ny

0.97

nie

0.93

ason

0.90

athan

0.89

jon

0.88

onymous

0.86

 Hopkins

0.85

uments

0.85

Activations Density 0.006%

names related to Jon

mentions of the name "Jon"

No Comments

No Known Activations