INDEX

Explanations

assertive statements related to subjective opinions or evaluations

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.72

MessageOf

-0.76

+:+

-0.73

styleType

-0.73

NamedQueries

-0.69

InjectAttribute

-0.68

sizeCache

-0.68

Referències

-0.67

DeleteBehavior

-0.67

usercontent

-0.65

POSITIVE LOGITS

 milf

1.44

 maneu

1.44

 shenan

1.43

 disreg

1.42

 madonna

1.41

 🤣🤣

1.38

 peppa

1.35

 tupperware

1.35

 wikihow

1.32

 indestru

1.29

Activations Density 0.143%

assertive statements related to subjective opinions or evaluations

No Comments

No Known Activations