INDEX

Explanations

specific technical or conditional terminology related to systems or processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ThroughAttribute

-0.64

 isolated

-0.47

Isolation

-0.44

 either

-0.43

TintMode

-0.43

mbggenerated

-0.42

bee

-0.41

dailymail

-0.41

 isolé

-0.40

عين

-0.39

POSITIVE LOGITS

+#+#

0.82

 autorytatywna

0.79

MemoryWarning

0.78

RectangleBorder

0.77

enderror

0.74

 linkovi

0.74

 dynam

0.69

 ExecuteAsync

0.67

IsContent

0.66

CreateMap

0.66

Activations Density 0.004%

specific technical or conditional terminology related to systems or processes

No Comments

No Known Activations