INDEX

Explanations

phrases indicating opinions or commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 محفوظة

-0.62

//</

-0.60

ubri

-0.59

AccessorTable

-0.59

complexContent

-0.58

 AssemblyVersion

-0.57

interopRequire

-0.57

errHandler

-0.57

 فريبيس

-0.56

 NavController

-0.56

POSITIVE LOGITS

 Yesterday

0.66

 yesterday

0.65

Yesterday

0.63

 Elsewhere

0.60

UPDATE

0.59

今週

0.58

というわけで

0.58

uxxxx

0.58

Elsewhere

0.57

 tonight

0.57

Activations Density 0.215%

phrases indicating opinions or commentary

No Comments

No Known Activations