INDEX

Explanations

phrases related to programming and document manipulation

oai_token-act-pair · gpt-3.5-turbo

references to documents and their structure

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

é¾įå

-0.84

vernment

-0.80

peria

-0.73

xual

-0.70

 Flavoring

-0.69

å§«

-0.69

emale

-0.68

erous

-0.67

cffffcc

-0.67

ethy

-0.67

POSITIVE LOGITS

 handler

0.89

 namespace

0.82

handler

0.82

Content

0.81

 configuration

0.79

 builder

0.78

builder

0.78

ynchron

0.78

 context

0.77

 HTTP

0.77

Activations Density 0.238%

phrases related to programming and document manipulation

references to documents and their structure

No Comments

No Known Activations