INDEX

Explanations

references to specific proteins and their associated functions in biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 ―――――

-1.09

 Theſe

-1.08

 ་་

-1.05

 Monfieur

-0.96

 Houſe

-0.96

 Anſ

-0.96

ſelf

-0.96

 itſelf

-0.94

 myſelf

-0.94

 ſind

-0.91

POSITIVE LOGITS

 faca

0.62

ing

0.57

 vortices

0.57

 '../../

0.57

0.56

tla

0.56

httphttps

0.54

glPushMatrix

0.54

PointSize

0.54

Activations Density 0.028%

references to specific proteins and their associated functions in biological processes

No Comments

No Known Activations