INDEX

Explanations

markers for significant data or structural elements in a document

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

 iprot

-0.66

 oprot

-0.61

 disc

-0.58

 AssemblyCulture

-0.56

trit

-0.55

RegressionTest

-0.54

anes

-0.54

 Disc

-0.53

 tand

-0.51

obot

-0.50

POSITIVE LOGITS

expandindo

0.70

<blockquote>

0.60

styleable

0.58

rungsseite

0.53

 bParam

0.52

IMPORTED

0.51

modore

0.51

żd

0.49

\{\\

0.49

steamcommunity

0.48

Activations Density 0.007%

markers for significant data or structural elements in a document

No Comments

No Known Activations