INDEX

Explanations

technical or programming-related terminology within the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

Efq

-0.84

 Monfieur

-0.82

DataContract

-0.79

 myſelf

-0.78

 Theſe

-0.74

GEBURTS

-0.72

 pleaſure

-0.72

 doubtnut

-0.71

 Reſ

-0.70

 himo

-0.69

POSITIVE LOGITS

<tr>

0.93

帖最后由

0.77

</thead>

0.76

 חיצוניים

0.74

הערות

0.64

\{\\

0.61

<bos>

0.59

.*")]

0.59

enumi

0.58

 also

0.57

Activations Density 0.023%

technical or programming-related terminology within the text

No Comments

No Known Activations