INDEX

Explanations

references to frameworks and structures in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Parcelize

-0.98

 HasFactory

-0.93

 createSlice

-0.92

 tué

-0.82

MigrationBuilder

-0.75

makeText

-0.71

!*\

-0.70

 électron

-0.69

 Ethn

-0.68

 CELLS

-0.67

POSITIVE LOGITS

 framework

2.00

 Framework

1.90

Framework

1.85

 frameworks

1.82

framework

1.74

 Frameworks

1.49

 FRAMEWORK

1.38

框架

1.07

 groundwork

0.87

CrossRef

0.77

Activations Density 0.088%

references to frameworks and structures in various contexts

No Comments

No Known Activations