INDEX

Explanations

statements showing seriousness, concern, or action towards specific issues or incidents

oai_token-act-pair · gpt-3.5-turbo

terms related to serious concerns or allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ificent

-0.64

 Smile

-0.64

 Retrieved

-0.62

 Machina

-0.60

regate

-0.58

etheless

-0.58

alde

-0.57

otten

-0.57

 Stretch

-0.56

 wonders

-0.54

POSITIVE LOGITS

 seriously

1.54

 Seriously

1.26

 aback

1.06

 hostage

1.06

 lightly

0.98

 offline

0.88

 into

0.87

 stride

0.84

 literally

0.84

 VERY

0.83

Activations Density 0.105%

statements showing seriousness, concern, or action towards specific issues or incidents

terms related to serious concerns or allegations

No Comments

No Known Activations