INDEX

Explanations

a variety of tokens, possibly related to identifiers or data points

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

-0.66

-0.64

 PLWABN

-0.61

PreferredItem

-0.61

richTextPanel

-0.56

তথ্যসূত্র

-0.54

 FetchType

-0.53

#+#

-0.52

 positional

-0.52

POSITIVE LOGITS

 незавершена

0.58

 "..\..\..\

0.52

</thead>

0.47

advice

0.44

Enllaces

0.43

wiesen

0.43

 الرياضيه

0.42

iglio

0.42

 ͡°)

0.42

ñores

0.42

Activations Density 0.192%

a variety of tokens, possibly related to identifiers or data points

No Comments

No Known Activations