INDEX

Explanations

content related to testing and debugging processes

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

Simulating, mimicking, or replicating something else

np_acts-logits-general · gemini-2.0-flash

create or mimic models

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Upan

-0.62

LETIN

-0.61

 myſelf

-0.59

DotNetBar

-0.58

 iſt

-0.56

 récompense

-0.55

 Kombin

-0.55

сылкі

-0.55

 Wiktionnaire

-0.55

essä

-0.54

POSITIVE LOGITS

 simulate

2.14

 simulated

2.09

 simulating

2.05

 simulates

2.03

 mimic

1.96

 simulation

1.89

 mimicking

1.87

 imitation

1.87

 mimics

1.82

 imit

1.78

Activations Density 0.493%

content related to testing and debugging processes

Simulating, mimicking, or replicating something else

create or mimic models

No Comments

No Known Activations