INDEX

Explanations

details related to professional roles and affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

AndEndTag

-0.89

 utafitiHapana

-0.80

 Theſe

-0.79

 vectorielle

-0.76

 themſelves

-0.73

horabuena

-0.73

 vettoriale

-0.72

 pngtree

-0.71

 poffible

-0.69

 auffi

-0.69

POSITIVE LOGITS

 mainly

0.61

mainly

0.59

 mostly

0.54

mostly

0.52

 primarily

0.50

ajax

0.47

нато

0.47

 macam

0.47

 Mainly

0.46

0.45

Activations Density 0.195%

details related to professional roles and affiliations

No Comments

No Known Activations