INDEX

Explanations

terms related to practical applications or uses

oai_token-act-pair · gpt-3.5-turbo

references to practical applications or uses of topics discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 parting

-0.67

olic

-0.67

ahon

-0.63

 clenched

-0.62

ramid

-0.60

ãĥ³ãĤ¸

-0.60

 advoc

-0.58

llor

-0.56

 incorpor

-0.55

lear

-0.54

POSITIVE LOGITS

ability

0.91

 status

0.80

due

0.78

 somewhere

0.76

 anywhere

0.76

places

0.76

 thanks

0.76

 muster

0.76

due

0.73

 elsewhere

0.73

Activations Density 0.330%

terms related to practical applications or uses

references to practical applications or uses of topics discussed

No Comments

No Known Activations