INDEX

Explanations

references to roles and titles within various organizations and professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

"])

-0.54

"]="

-0.51

 noten

-0.51

'])->

-0.50

()]

-0.48

ullen

-0.48

"]

-0.47

velope

-0.47

áng

-0.46

Portale

-0.46

POSITIVE LOGITS

 kasarigan

0.76

AutoScaleMode

0.71

principalColumn

0.69

SuccessListener

0.67

SourceChecksum

0.66

 jsPsych

0.63

DeleteBehavior

0.62

UseVisualStyle

0.61

memoized

0.61

 Bioaccumulative

0.60

Activations Density 0.314%

references to roles and titles within various organizations and professions

No Comments

No Known Activations