INDEX

Explanations

terms related to coding or technical instructions

oai_token-act-pair · gpt-3.5-turbo

specific letters and their combinations, particularly in contexts involving ratings and alphanumeric sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

advertising

-0.79

 fulfillment

-0.70

 condem

-0.68

Gaza

-0.61

miss

-0.57

guards

-0.57

effects

-0.56

waters

-0.56

ritis

-0.55

Disclaimer

-0.55

POSITIVE LOGITS

EStream

0.75

é¾

0.75

ŃĶ

0.75

 laureate

0.73

xual

0.70

xon

0.67

EStreamFrame

0.66

ãĥĺãĥ©

0.64

ullivan

0.62

ENG

0.62

Activations Density 0.224%

terms related to coding or technical instructions

specific letters and their combinations, particularly in contexts involving ratings and alphanumeric sequences

No Comments

No Known Activations