INDEX

Explanations

numeric values and representations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

تقاوى

-0.55

Pautan

-0.55

<>

-0.53

Portail

-0.52

SourceChecksum

-0.51

warzys

-0.51

 >=",

-0.50

'{@

-0.48

Portale

-0.47

worthiness

-0.47

POSITIVE LOGITS

<eos>

0.81

↵

0.69

↵↵↵

0.68

↵↵↵↵↵↵

0.67

 invokingState

0.66

 endforeach

0.64

↵↵↵↵↵↵↵

0.62

↵↵↵↵

0.62

 estekak

0.60

↵↵↵↵↵↵↵↵↵

0.60

Activations Density 0.504%

numeric values and representations in various contexts

No Comments

No Known Activations