INDEX

Explanations

references to medical conditions and treatments

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

Follows "to," "the," or "if."

np_acts-logits-general · gemini-2.0-flash

sequences starting with "to" or "the"

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Meanwhile

-0.62

 meanwhile

-0.54

 Meanwhile

-0.51

 noqa

-0.48

 adequately

-0.47

 surla

-0.47

urysty

-0.45

IComponent

-0.45

šanai

-0.44

eriks

-0.44

POSITIVE LOGITS

Hentet

0.74

出版年

0.67

arakhand

0.59

themselves

0.55

最快更新

0.55

shame

0.54

himself

0.54

 offending

0.53

 himself

0.53

herself

0.52

Activations Density 0.026%

references to medical conditions and treatments

Follows "to," "the," or "if."

sequences starting with "to" or "the"

No Comments

No Known Activations