INDEX

Explanations

references to specific categories or types of items

oai_token-act-pair · gpt-3.5-turbo

references to examples or types of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

olute

-0.68

YR

-0.68

inka

-0.62

 somew

-0.61

onel

-0.61

eland

-0.58

olina

-0.58

enger

-0.57

orem

-0.57

ysical

-0.57

POSITIVE LOGITS

ties

0.85

ities

0.77

deals

0.67

Flag

0.63

sword

0.62

inyl

0.61

complex

0.61

Arg

0.60

 gems

0.58

 outsourcing

0.57

Activations Density 0.043%

references to specific categories or types of items

references to examples or types of things

No Comments

No Known Activations