INDEX

Explanations

lines of code or specific programming constructs and related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 pains

-0.46

 rates

-0.44

乎

-0.43

 Polly

-0.43

こと

-0.42

TagHelper

-0.42

ばかり

-0.42

 sóng

-0.42

Baldwin

-0.42

 cale

-0.41

POSITIVE LOGITS

complexContent

0.85

 Meksiku

0.84

 propOrder

0.74

 Савезне

0.74

Chham

0.71

Portail

0.65

 Roskov

0.64

Portale

0.64

OGND

0.62

FZ

0.61

Activations Density 0.406%

lines of code or specific programming constructs and related syntax

No Comments

No Known Activations