INDEX

Explanations

pointers and references 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 @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Rosenthal

-0.93

CppMethod

-0.79

/**

-0.76

 Sampson

-0.74

kont

-0.73

р

-0.72

 Brin

-0.72

Tre

-0.71

 delan

-0.71

Kel

-0.70

POSITIVE LOGITS

Efq

1.22

 themſelves

1.12

 Theſe

1.10

 itſelf

1.09

 myſelf

1.08

 uſed

1.07

 Monfieur

1.01

 pleaſure

0.97

 Jefus

0.97

 fevere

0.95

Activations Density 0.863%

pointers and references in code

No Comments

No Known Activations