INDEX

Explanations

references to specific items or objects

oai_token-act-pair · gpt-3.5-turbo

the word "these" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

erate

-0.78

Disk

-0.73

hood

-0.73

VW

-0.72

igation

-0.71

atform

-0.71

iness

-0.70

achus

-0.70

herty

-0.69

esm

-0.69

POSITIVE LOGITS

 guys

0.94

 fellows

0.84

 kinds

0.80

 sights

0.79

 lovely

0.76

 Situation

0.76

 darn

0.76

 nifty

0.74

 sorts

0.74

 crazy

0.69

Activations Density 0.095%

references to specific items or objects

the word "these" in various contexts

No Comments

No Known Activations