INDEX

Explanations

phrases related to control and agency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

RenderAtEndOf

-0.75

sidemargin

-0.58

Pyx

-0.57

IUrlHelper

-0.57

 nakalista

-0.56

TagHelpers

-0.55

ValueStyle

-0.54

gore

-0.53

__(/*!

-0.52

 cote

-0.50

POSITIVE LOGITS

 uncontrollable

0.70

 controllable

0.64

 factors

0.59

 ainfi

0.57

 Caused

0.56

 виправивши

0.56

 hasard

0.56

 changeable

0.54

 caused

0.53

Causes

0.53

Activations Density 0.301%

phrases related to control and agency in various contexts

No Comments

No Known Activations