INDEX

Explanations

instances where the word "Start" is emphasized or repeated

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Start."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 conveyed

-0.64

 aven

-0.64

uro

-0.63

 graded

-0.62

 concealed

-0.62

 clad

-0.61

bos

-0.60

 corrobor

-0.60

 sustained

-0.59

 unseen

-0.59

POSITIVE LOGITS

 Start

3.65

Start

2.40

start

2.10

 START

2.04

 Starts

1.94

 start

1.90

 Begin

1.61

 Startup

1.49

 Starting

1.44

starting

1.38

Activations Density 0.012%

instances where the word "Start" is emphasized or repeated

instances of the word "Start."

No Comments

No Known Activations