INDEX

Explanations

adverse events related to medical treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

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

 matricula

-0.44

InjectMocks

-0.44

Meet

-0.43

 edin

-0.41

medlem

-0.41

 Burg

-0.40

"])){

-0.40

mentable

-0.39

obium

-0.39

set

-0.39

POSITIVE LOGITS

 adverse

0.84

 effects

0.83

kloped

0.81

AndEndTag

0.79

principalColumn

0.75

effects

0.74

 Adverse

0.73

 Effects

0.72

RegressionTest

0.72

 Nebenwirkungen

0.71

Activations Density 0.701%

adverse events related to medical treatments

No Comments

No Known Activations