INDEX

Explanations

terms related to the progression and characteristics of medical conditions or behavioral patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

elsey

-0.55

 morire

-0.54

 circonst

-0.54

 prokary

-0.50

 établissements

-0.50

 tibi

-0.49

 lado

-0.49

 Revital

-0.48

 Lait

-0.48

 Relief

-0.48

POSITIVE LOGITS

 trajectory

1.00

 paths

0.98

 course

0.95

 path

0.94

 trajectories

0.94

 behaviour

0.87

 behavior

0.86

 pattern

0.86

 progression

0.85

course

0.85

Activations Density 0.502%

terms related to the progression and characteristics of medical conditions or behavioral patterns

No Comments

No Known Activations