INDEX

Explanations

references to medical entities or organizations

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

 Landschaft

-0.45

 Spuren

-0.44

 škoda

-0.43

 keluarganya

-0.40

 législ

-0.40

 Inseln

-0.40

 Voraussetzungen

-0.39

Efq

-0.39

 ibunya

-0.39

 Könige

-0.39

POSITIVE LOGITS

Ref

0.66

 Medical

0.64

сылкі

0.60

REF

0.57

 plea

0.57

 lenker

0.57

ref

0.56

Ref

0.55

 medical

0.55

REF

0.55

Activations Density 0.378%

references to medical entities or organizations

No Comments

No Known Activations