INDEX

Explanations

terms related to assignments or assigning responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 penyel

-0.76

 Barrow

-0.71

COOK

-0.68

 Overton

-0.67

/\.

-0.67

 vectorielle

-0.66

shund

-0.66

 doute

-0.65

 jurí

-0.63

DOC

-0.62

POSITIVE LOGITS

 assignment

2.06

 assign

2.06

 assigns

1.97

 assignments

1.94

 ASSIGN

1.93

 Assignments

1.88

 Assign

1.88

 assig

1.87

 assigned

1.85

ASSIGN

1.85

Activations Density 0.081%

terms related to assignments or assigning responsibilities

No Comments

No Known Activations