INDEX

Explanations

specific names or identifiers, likely related to individuals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.76

SequentialGroup

-0.74

RTHOOK

-0.70

ScopeManager

-0.70

 وتسجيلات

-0.69

 صوتيه

-0.67

SOUNDBITE

-0.67

 defaultstate

-0.65

ornata

-0.64

AddHtmlAttribute

-0.64

POSITIVE LOGITS

antine

0.54

Form

0.53

 Form

0.52

form

0.52

FORM

0.52

then

0.52

лой

0.50

Em

0.49

Em

0.49

 Samuel

0.48

Activations Density 0.113%

specific names or identifiers, likely related to individuals

No Comments

No Known Activations