INDEX

Explanations

concepts related to analysis and assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

-1.02

-0.85

-0.79

-0.76

-0.67

<eos>

-0.63

-0.62

-0.61

...

-0.60

POSITIVE LOGITS

Efq

1.32

mybatisplus

1.27

 resourceCulture

1.25

 TestBed

1.20

StoryboardSegue

1.17

 InputDecoration

1.17

 leaſt

1.16

NUMX

1.13

 IBOutlet

1.12

 MainAxisSize

1.11

Activations Density 1.134%

concepts related to analysis and assessment

No Comments

No Known Activations