INDEX

Explanations

connections and associations between concepts or entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 leçons

-0.58

 suprême

-0.57

 composizione

-0.57

 pitié

-0.56

 aguda

-0.56

 silencioso

-0.55

 '.';

-0.55

 exemplaires

-0.54

 entgegen

-0.53

 shutil

-0.52

POSITIVE LOGITS

 linked

0.96

 related

0.95

 relates

0.91

 Linked

0.90

Linked

0.89

tagHelperRunner

0.88

related

0.88

 tied

0.85

rungsseite

0.85

 relation

0.84

Activations Density 0.425%

connections and associations between concepts or entities

No Comments

No Known Activations