INDEX

Explanations

repeated patterns or structures in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

\#:

-0.51

dule

-0.45

 Ebers

-0.44

 насељу

-0.43

en

-0.43

 numb

-0.43

 press

-0.42

 machine

-0.42

 normally

-0.42

numb

-0.41

POSITIVE LOGITS

 незавершена

0.95

 rowspan

0.92

 فريبيس

0.76

 GetEnumerator

0.76

extAlignment

0.75

 colspan

0.74

 StatefulWidget

0.65

</tr>

0.61

 Walkover

0.60

 minOccurs

0.58

Activations Density 0.034%

repeated patterns or structures in a dataset

No Comments

No Known Activations