INDEX

Explanations

references to layers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 OMITBAD

-0.59

 désolés

-0.59

Демографія

-0.58

 OnInit

-0.55

]")]

-0.54

URLException

-0.53

ьаж

-0.52

 NavController

-0.52

ußt

-0.52

WebServlet

-0.52

POSITIVE LOGITS

 layer

2.31

 Layer

2.19

layer

2.14

Layer

2.11

 layers

2.09

 LAYER

1.98

 Layers

1.96

layers

1.86

Layers

1.73

 layered

1.73

Activations Density 0.173%

references to layers in various contexts

No Comments

No Known Activations