INDEX

Explanations

technical terms related to formatting and programming languages

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</em>

-0.49

et

-0.48

New

-0.47

bona

-0.46

lap

-0.46

 which

-0.45

 thank

-0.44

my

-0.44

 plain

-0.44

POSITIVE LOGITS

tvguidetime

1.11

 iprot

1.02

المناصب

0.97

 autorytatywna

0.93

IsMutable

0.93

FunctionFlags

0.92

 referenties

0.92

 Cassini

0.87

 betweenstory

0.87

 Agamemnon

0.86

Activations Density 1.704%

technical terms related to formatting and programming languages

No Comments

No Known Activations