INDEX

Explanations

references to geographical regions and political relationships

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

Personendaten

-0.82

 Normdatei

-0.72

+};

-0.67

SourceChecksum

-0.63

érité

-0.62

Hochspringen

-0.61

➟

-0.60

neuf

-0.60

 fieldNum

-0.59

AddField

-0.59

POSITIVE LOGITS

seamnă

0.62

 downtown

0.62

 cosmopolitan

0.58

 modern

0.57

 contemporary

0.57

localctx

0.57

 Monfieur

0.56

 neighbouring

0.54

 neighboring

0.53

 present

0.52

Activations Density 0.327%

references to geographical regions and political relationships

No Comments

No Known Activations