INDEX

Explanations

terms related to decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 سكانية

-0.68

✨:

-0.66

 мәкалә

-0.64

انيف

-0.62

 disambiguazione

-0.62

StructEnd

-0.62

ugc

-0.60

 jspb

-0.60

isome

-0.59

 sociaux

-0.59

POSITIVE LOGITS

 makers

0.84

makers

0.77

 Decision

0.71

 maker

0.69

maker

0.67

 decision

0.66

 Decisions

0.66

 DECISION

0.64

 trees

0.63

 Maker

0.63

Activations Density 0.076%

terms related to decision-making processes

No Comments

No Known Activations