INDEX

Explanations

patterns or structures in the presentation of data, particularly in statistical expressions or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

TagMode

-0.56

twimg

-0.44

 ente

-0.43

تقاوى

-0.43

ButtonClick

-0.42

laise

-0.42

OLIS

-0.40

 bouch

-0.40

娱乐

-0.40

 secund

-0.40

POSITIVE LOGITS

pexpr

0.50

UnusedPrivate

0.40

NameInMap

0.40

CppMethod

0.38

0.37

flink

0.37

arraycopy

0.37

ftagPool

0.36

outWeight

0.36

 resourceCulture

0.36

Activations Density 0.350%

patterns or structures in the presentation of data, particularly in statistical expressions or results

No Comments

No Known Activations