INDEX

Explanations

references to motivations and justifications for actions in terms of self-interest or defense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessorTable

-0.70

matchCondition

-0.69

rigkeit

-0.61

BagConstraints

-0.60

mybatisplus

-0.59

 florales

-0.59

TagHelper

-0.59

ColumnHeaders

-0.59

ivamente

-0.58

 tantôt

-0.58

POSITIVE LOGITS

 purposes

0.66

 purpose

0.62

 reinen

0.56

 pure

0.55

 Purposes

0.55

hirt

0.53

pure

0.52

 Purpose

0.51

 PURPOSE

0.51

âu

0.50

Activations Density 0.423%

references to motivations and justifications for actions in terms of self-interest or defense

No Comments

No Known Activations