INDEX

Explanations

combinations of actions and their consequences, particularly relating to life and death choices

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

StructEnd

-0.86

findpost

-0.75

PMailer

-0.75

LookAnd

-0.72

AddHtmlAttribute

-0.70

 mxArray

-0.68

GraphicsUnit

-0.68

ftagPool

-0.68

✭✭

-0.68

htaccess

-0.67

POSITIVE LOGITS

 conclusione

0.44

orm

0.44

 Part

0.43

 peran

0.42

low

0.42

Reviewed

0.41

Try

0.41

 part

0.41

 your

0.41

 almeno

0.40

Activations Density 0.383%

combinations of actions and their consequences, particularly relating to life and death choices

No Known Activations