INDEX

Explanations

professional industry terminologies and reference companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 AssemblyCulture

-0.64

CLUYE

-0.62

CodeAnalysis

-0.55

 Bioaccumulative

-0.54

SequentialGroup

-0.54

Spotify

-0.54

 Hodgkin

-0.54

 Spotify

-0.54

="@+

-0.53

 Condé

-0.53

POSITIVE LOGITS

 product

0.77

 products

0.75

 manufacturers

0.68

Products

0.68

 manufacturer

0.68

 Products

0.67

 solutions

0.66

products

0.66

 industrial

0.66

 manufacture

0.66

Activations Density 0.381%

professional industry terminologies and reference companies

No Comments

No Known Activations