INDEX

Explanations

instances of significant actions or events in the context of narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 drauf

-0.46

事的

-0.43

rentices

-0.42

mazoo

-0.42

COLOG

-0.41

Derp

-0.41

 înc

-0.41

URLException

-0.41

nių

-0.41

tokine

-0.41

POSITIVE LOGITS

 resourceCulture

0.76

expandindo

0.66

 <>",

0.65

Sucesor

0.59

 <=",

0.57

bindingNavigator

0.57

/*

0.57

 OFDb

0.57

hoeddwyd

0.56

ftagPool

0.55

Activations Density 0.737%

instances of significant actions or events in the context of narratives

No Comments

No Known Activations