INDEX

Explanations

terms associated with taxi drivers and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 CreateTagHelper

-0.45

FormsModule

-0.38

izacin

-0.37

rrggbb

-0.36

ClientSize

-0.35

 GenerationType

-0.35

PerformLayout

-0.35

 Chemicals

-0.35

Enllaces

-0.34

égio

-0.34

POSITIVE LOGITS

 taxi

1.97

 Taxi

1.77

 taxis

1.70

 Uber

1.67

taxi

1.64

cab

1.63

Taxi

1.61

 cabs

1.59

Uber

1.52

 такси

1.34

Activations Density 0.165%

terms associated with taxi drivers and related activities

No Comments

No Known Activations