INDEX

Explanations

terms related to incidents and incubation processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]**

-0.74

 Reeves

-0.70

 Poster

-0.67

 Shaun

-0.66

 Salas

-0.66

kehrt

-0.64

Sutton

-0.64

 Waller

-0.63

θεν

-0.63

dav

-0.61

POSITIVE LOGITS

INC

1.23

inc

1.08

 Incidents

1.07

Inc

1.05

Inc

1.02

 متعلقه

1.02

INC

0.99

 incidents

0.99

inc

0.94

 myſelf

0.91

Activations Density 0.070%

terms related to incidents and incubation processes

No Comments

No Known Activations