INDEX

Explanations

references to specific parts or components, especially in the context of technical discussions

oai_token-act-pair · gpt-3.5-turbo

references to various types of parts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idav

-0.81

pub

-0.70

 FANTASY

-0.70

opa

-0.68

Draft

-0.65

endi

-0.65

ricanes

-0.64

icz

-0.64

CHAT

-0.64

fm

-0.63

POSITIVE LOGITS

meal

0.96

ridges

0.85

 parts

0.77

kit

0.73

ials

0.72

 recy

0.72

 Repair

0.71

 Kits

0.71

 Components

0.71

 thereof

0.70

Activations Density 0.028%

references to specific parts or components, especially in the context of technical discussions

references to various types of parts

No Comments

No Known Activations