INDEX

Explanations

references to software updates or version improvements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BoxDecoration

-0.64

NUMX

-0.61

ientôt

-0.61

 nahilalakip

-0.59

 initComponents

-0.58

 Walkover

-0.56

 CommandType

-0.56

 mergeFrom

-0.55

apunov

-0.55

featureID

-0.54

POSITIVE LOGITS

 soucis

0.52

τως

0.51

完美的

0.51

很多的

0.50

 Proprietary

0.49

不一样的

0.48

不错的

0.47

极致

0.47

 bedrag

0.47

 Flexibility

0.46

Activations Density 0.021%

references to software updates or version improvements

No Comments

No Known Activations