INDEX

Explanations

terms related to medical conditions and treatments

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

Follows less-common capitalized words

np_acts-logits-general · gemini-2.0-flash

Scorpio reforms, cannot tell, respiratory distress

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

 BorderSide

-0.59

 виправивши

-0.57

iduous

-0.56

 sometimes

-0.56

 fermés

-0.55

 jährlich

-0.55

 often

-0.55

opardy

-0.54

sometimes

-0.54

 weekends

-0.54

POSITIVE LOGITS

 Meanwhile

0.64

 flashback

0.61

Meanwhile

0.61

 unconscious

0.60

 rescue

0.60

 disguised

0.59

 rescat

0.58

 rescuing

0.56

adpleegd

0.56

 confronting

0.55

Activations Density 0.391%

terms related to medical conditions and treatments

Follows less-common capitalized words

Scorpio reforms, cannot tell, respiratory distress

No Comments

No Known Activations