INDEX

Explanations

associations or references to television programs and their hosts

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

 دانلود

-0.48

 przew

-0.47

 Rebellion

-0.46

 Confederacy

-0.45

 strdup

-0.45

 лето

-0.44

 fiore

-0.43

teks

-0.43

tagHelper

-0.43

 deposited

-0.43

POSITIVE LOGITS

 show

0.75

CodeAttribute

0.71

 program

0.67

 broadcast

0.67

 radio

0.67

jsxFileName

0.66

 interviewer

0.65

 televis

0.65

 QName

0.64

Extinguishing

0.64

Activations Density 0.156%

associations or references to television programs and their hosts

No Comments

No Known Activations