INDEX

Explanations

terms related to inputs and outputs in electronic circuits

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

The token "input"

np_acts-logits-general · gemini-2.0-flash

input followed by context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 jorden

-0.73

 métallique

-0.73

 posteriore

-0.72

 Berikut

-0.71

 cohomology

-0.70

 morire

-0.69

 antaranya

-0.69

HTC

-0.68

zeppelin

-0.68

 exclusivas

-0.68

POSITIVE LOGITS

 INPUT

1.33

 input

1.27

 inputs

1.25

 Input

1.23

INPUT

1.19

 Inputs

1.19

setInput

1.13

 输入

1.08

Input

1.07

Inputs

1.04

Activations Density 0.101%

terms related to inputs and outputs in electronic circuits

The token "input"

input followed by context

No Comments

No Known Activations