INDEX

Explanations

items related to tutorials

oai_token-act-pair · gpt-3.5-turbo

references to tutorials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

itol

-0.77

oples

-0.74

inion

-0.69

olitics

-0.67

och

-0.66

minster

-0.65

ceptions

-0.65

oustic

-0.65

olls

-0.65

ppelin

-0.63

POSITIVE LOGITS

STEP

0.84

 tutorials

0.83

 Tutorial

0.81

 tutorial

0.81

 Guide

0.77

Course

0.72

 Guides

0.70

 guide

0.70

 STEP

0.69

 guides

0.69

Activations Density 0.022%

items related to tutorials

references to tutorials

No Comments

No Known Activations