INDEX

Explanations

proper nouns, likely related to individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of commas in sentences

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

 cartridges

-0.68

planes

-0.67

 calendar

-0.64

ãĥ¥

-0.63

Characters

-0.62

 status

-0.62

 incon

-0.62

 format

-0.61

 prompt

-0.61

bucks

-0.61

POSITIVE LOGITS

Jr

1.38

Sr

1.17

tein

1.02

aka

1.01

Jr

0.95

MD

0.89

PhD

0.89

QC

0.80

 Managing

0.76

who

0.75

Activations Density 0.216%

proper nouns, likely related to individuals

occurrences of commas in sentences

No Comments

No Known Activations