INDEX

Explanations

tech-related terms, specifically related to Microsoft OneNote and web applications

oai_token-act-pair · gpt-3.5-turbo

references to specific technologies or software applications

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

 Entered

-0.96

 Hogan

-0.61

 Floyd

-0.57

 seism

-0.56

 Hutchinson

-0.54

 Fang

-0.53

Ung

-0.52

 Gutenberg

-0.51

 Vaughan

-0.51

 Ulster

-0.50

POSITIVE LOGITS

 itself

0.72

ktop

0.62

orean

0.61

orea

0.58

 teasp

0.57

brids

0.56

ngth

0.55

Condition

0.55

rect

0.55

shapeshifter

0.55

Activations Density 1.825%

tech-related terms, specifically related to Microsoft OneNote and web applications

references to specific technologies or software applications

No Comments

No Known Activations