INDEX

Explanations

occurrences of the term "dot" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

guiente

-0.53

extré

-0.53

 noDo

-0.50

 burbu

-0.49

 Monfieur

-0.48

 subterrá

-0.47

ientras

-0.47

 autorytatywna

-0.46

 parejas

-0.46

 negru

-0.45

POSITIVE LOGITS

Et

0.80

Et

0.65

dot

0.64

dot

0.62

SpringRunner

0.61

melt

0.60

 melts

0.60

Dot

0.60

mel

0.59

Dot

0.57

Activations Density 0.236%

occurrences of the term "dot" in various contexts

No Comments

No Known Activations