INDEX

Explanations

keywords related to receiving or accepting information or visitors

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-1.09

+#+#

-0.88

 تضيفلها

-0.82

 Monfieur

-0.81

twimg

-0.81

RTDA

-0.78

 Мексичка

-0.76

"]];

-0.76

ImageContext

-0.76

 fubject

-0.72

POSITIVE LOGITS

 accept

0.71

 diterima

0.69

 accepts

0.64

accepts

0.64

 accepted

0.60

 acceptance

0.60

 menerima

0.60

 aceptar

0.58

 Accept

0.57

 akzep

0.57

Activations Density 0.266%

keywords related to receiving or accepting information or visitors

No Comments

No Known Activations