INDEX

Explanations

words related to specific names or titles

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.66

 compan

-0.59

 Dise

-0.58

 conduc

-0.56

Den

-0.55

 conflic

-0.55

Fn

-0.55

CONCLUS

-0.55

ãĥ£

-0.54

CLASSIFIED

-0.54

POSITIVE LOGITS

nik

0.74

oda

0.72

amer

0.70

opa

0.67

ofer

0.66

si

0.64

la

0.64

anski

0.63

oe

0.63

iew

0.63

Activations Density 0.324%

words related to specific names or titles

abbreviations and acronyms

No Comments

No Known Activations