INDEX

Explanations

words and phrases related to the specification and analysis of data structures and programming

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

CodedInputStream

-0.85

UnusedPrivate

-0.84

Personendaten

-0.83

 dAtA

-0.81

 unknownFields

-0.78

AccessorTable

-0.77

SourceChecksum

-0.75

DebuggerNonUser

-0.74

rawDesc

-0.74

IsContent

-0.71

POSITIVE LOGITS

 Romains

0.77

thood

0.66

 peines

0.64

 prêtres

0.63

 larmes

0.60

 Juifs

0.56

>[]

0.56

 sœurs

0.56

 œuvres

0.54

 navires

0.54

Activations Density 1.408%

words and phrases related to the specification and analysis of data structures and programming

No Comments

No Known Activations