INDEX

Explanations

markers indicating significant events or alerts within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 esteja

-0.50

ßerdem

-0.48

-0.44

begin

-0.43

っ

-0.42

 Ressources

-0.42

 муніципалі

-0.40

alnya

-0.40

unción

-0.38

 FishBase

-0.38

POSITIVE LOGITS



0.89

AnimationsModule

0.82

 Мексичка

0.80

etc

0.77

Etc

0.76

Personendaten

0.76

 للمعارف

0.75

argout

0.75

 Administrativna

0.74

etc

0.73

Activations Density 0.422%

markers indicating significant events or alerts within a narrative context

No Comments

No Known Activations