INDEX

Explanations

numerical expressions and values

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

uxxxx

-0.72

 '\\;'

-0.64

CloseOperation

-0.62

 kasarigan

-0.62

onomia

-0.60

aarrggbb

-0.57

oprote

-0.56

rungsseite

-0.55

 onCreateView

-0.55

IntoConstraints

-0.55

POSITIVE LOGITS

 modell

0.80

 model

0.77

 detail

0.76

 modeller

0.75

 Detail

0.73

kit

0.73

 decals

0.73

 modeling

0.72

模型

0.72

 modelling

0.69

Activations Density 0.138%

numerical expressions and values

No Comments

No Known Activations