INDEX

Explanations

instances of positional language or references to locations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

MigrationBuilder

-0.73

osoba

-0.72

)))),

-0.69

 protoimpl

-0.67

 Réponses

-0.66

DockStyle

-0.64

complexType

-0.60

 transfieras

-0.58

enment

-0.57

Rhestr

-0.56

POSITIVE LOGITS

Pictured

0.59

ρίες

0.56

 ABOVE

0.54

flashdata

0.53

 Image

0.52

Photo

0.52

 above

0.52

 photographed

0.51

 pictured

0.51

Photos

0.50

Activations Density 0.163%

instances of positional language or references to locations in context

No Comments

No Known Activations