INDEX

Explanations

references to specific locations, particularly cities and regions associated with 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 pierdas

-0.46

trun

-0.45

ism

-0.45

opa

-0.45

 شهرد

-0.45

Presenter

-0.44

fahr

-0.43

ala

-0.43

RunWith

-0.43

 themselves

-0.43

POSITIVE LOGITS

 myſelf

0.92

 itſelf

0.86

 nahilalakip

0.86

ſelves

0.85

^(@)

0.85

 ſeveral

0.83

MigrationBuilder

0.81

 raiſ

0.81

 ―――――

0.77

 purpoſe

0.76

Activations Density 0.269%

references to specific locations, particularly cities and regions associated with various contexts

No Comments

No Known Activations