INDEX

Explanations

code-related constructs, particularly those involving data structures and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

::_('

-0.55

енча

-0.51

ızlık

-0.49

 simplifié

-0.47

ldorf

-0.47

WillAppear

-0.46

ddots

-0.46

 Silvers

-0.46

śl

-0.45

 ngoại

-0.45

POSITIVE LOGITS

 TreeNode

0.76

TreeNode

0.71

ListNode

0.65

GEBURTSDATUM

0.65

 Node

0.65

 ListNode

0.63

 MenuView

0.62

 Nodo

0.60

Node

0.60

Diweddarwch

0.59

Activations Density 0.172%

code-related constructs, particularly those involving data structures and function definitions

No Comments

No Known Activations