INDEX

Explanations

frequency values and statistical data representations in a structured format

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

-0.47

 although

-0.46

ve

-0.45

er

-0.44

in

-0.44

-0.43

 rather

-0.43

-0.42

how

-0.42

 trước

-0.42

POSITIVE LOGITS

TypedDataSet

1.00

 Shakspeare

0.97

 greateſt

0.93

Efq

0.92

 occaf

0.91

 myſelf

0.91

 BorderRadius

0.91

 TextInputType

0.91

 pleaſure

0.90

NameInMap

0.88

Activations Density 0.417%

frequency values and statistical data representations in a structured format

No Comments

No Known Activations