INDEX

Explanations

references to input fields in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 initComponents

-0.75

 HasFactory

-0.73

SharedCtor

-0.72

Parcelize

-0.70

 joaat

-0.69

QtWidgets

-0.66

findpost

-0.64

ollectionView

-0.62

RTLD

-0.61

 Offisielt

-0.61

POSITIVE LOGITS

setInput

0.76

 INPUT

0.65

 输入

0.64

 into

0.63

ting

0.63

INPUT

0.61

 Inputs

0.60

 getInput

0.60

 Input

0.60

 INTO

0.59

Activations Density 0.144%

references to input fields in code

No Comments

No Known Activations