INDEX

Explanations

names of universities or colleges

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people or characters

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

ilver

-0.76

arily

-0.74

*/(

-0.73

egal

-0.70

itized

-0.70

keys

-0.69

 agric

-0.68

matic

-0.68

eers

-0.67

ryu

-0.64

POSITIVE LOGITS

aneers

0.86

Cox

0.80

ruary

0.77

oken

0.76

 Myers

0.75

 Kitt

0.75

ulia

0.72

ards

0.72

 Slater

0.71

Bry

0.71

Activations Density 0.038%

names of universities or colleges

proper nouns, specifically names of people or characters

No Comments

No Known Activations