INDEX

Explanations

references to significant events, actions, or decisions, often in a context of relationships or interpersonal dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ScopeManager

-0.60

 obecnie

-0.59

 сейчас

-0.59

ագրություններ

-0.59

 currently

-0.57

Ici

-0.56

now

-0.56

 teraz

-0.55

 Currently

-0.53

now

-0.52

POSITIVE LOGITS

 naquele

1.47

 daquele

1.45

那天

1.28

ese

1.24

 jenem

1.16

 later

1.15

quela

1.15

esa

1.13

Later

1.11

那一

1.10

Activations Density 0.477%

references to significant events, actions, or decisions, often in a context of relationships or interpersonal dynamics

No Comments

No Known Activations