INDEX

Explanations

instances of specific numerical identifiers and references to amending documents or cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Houſe

-0.77

 houſe

-0.71

<unused62>

-0.69

 purpoſe

-0.67

<unused63>

-0.67

<unused61>

-0.66

 pleaſure

-0.66

 auroit

-0.65

<unused60>

-0.64

 Diſ

-0.64

POSITIVE LOGITS

<bos>

1.77

’

1.07

0.87

he

0.64

the

0.63

‘

0.59

 those

0.58

in

0.57

‘

0.55

’，

0.55

Activations Density 0.000%

instances of specific numerical identifiers and references to amending documents or cases

No Comments

No Known Activations