INDEX

Explanations

references to television-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.57

 пер

-0.49

 Trust

-0.48

 kapa

-0.47

ProductID

-0.46

фан

-0.45

IDs

-0.44

ガイ

-0.43

 UnityEngine

-0.43

 essencial

-0.43

POSITIVE LOGITS

:✨

0.88

InstrumentedTest

0.80

tvguidetime

0.80

 CreateTagHelper

0.80

entyfik

0.79

 thrones

0.79

StructEnd

0.79

 Unesco

0.77

 المعيارى

0.74

Activations Density 0.286%

references to television-related content

No Comments

No Known Activations