INDEX

Explanations

phrases related to influential organizations and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

aarrggbb

-0.79

 חיצוניים

-0.72

ThroughAttribute

-0.71

 dataSnapshot

-0.68

 *)__

-0.64

 beginnetje

-0.61

ItemLayout

-0.60

RegressionTest

-0.58

 препратки

-0.58

}{@

-0.57

POSITIVE LOGITS

 himſelf

0.99

Efq

0.94

 Majefty

0.93

 myſelf

0.89

 Monfieur

0.86

 Jefus

0.84

 themſelves

0.81

ſelf

0.80

 ſhe

0.76

 againſt

0.75

Activations Density 0.858%

phrases related to influential organizations and their actions

No Comments

No Known Activations