INDEX

Explanations

instances where something is of significant importance or concern

oai_token-act-pair · gpt-3.5-turbo

statements that convey skepticism or doubt

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

-0.60

-0.57

Construct

-0.57

 future

-0.57

 ACTION

-0.57

ater

-0.56

ument

-0.55

ecycle

-0.54

Cause

-0.54

 Specifically

-0.54

POSITIVE LOGITS

 hardly

3.08

 scarcely

2.48

 barely

1.81

 seldom

1.55

 doubtless

1.49

 surely

1.43

 certainly

1.39

 rarely

1.37

 practically

1.37

 nowhere

1.31

Activations Density 0.014%

instances where something is of significant importance or concern

statements that convey skepticism or doubt

No Comments

No Known Activations