INDEX

Explanations

terms related to various objects and activities, including vehicles, machines, animals, and natural features

oai_token-act-pair · gpt-3.5-turbo

nouns related to objects or entities

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

ecause

-0.68

 Universities

-0.67

 Helpful

-0.64

 Flavoring

-0.63

 PsyNet

-0.61

âĸĴ

-0.60

\.

-0.60

Laughs

-0.58

 ______

-0.58

 Nights

-0.56

POSITIVE LOGITS

 consisted

0.85

 belonged

0.77

maker

0.72

 disappeared

0.72

 consists

0.72

 lasted

0.71

 itself

0.70

 vanished

0.70

washer

0.70

 contains

0.69

Activations Density 0.542%

terms related to various objects and activities, including vehicles, machines, animals, and natural features

nouns related to objects or entities

No Comments

No Known Activations