INDEX

Explanations

terms related to incidents or events with a focus on medical and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 fritas

-0.51

fml

-0.49

 stra

-0.49

Pier

-0.47

HLT

-0.47

 Lyons

-0.47

真正

-0.47

θεν

-0.47

hloromethane

-0.47

pier

-0.47

POSITIVE LOGITS

 Incidents

0.96

INC

0.96

inc

0.91

Inc

0.91

SequentialGroup

0.89

Inc

0.83

inc

0.82

INC

0.81

 incidents

0.81

 Cresc

0.77

Activations Density 0.126%

terms related to incidents or events with a focus on medical and scientific contexts

No Comments

No Known Activations