INDEX

Explanations

terms related to exposure and derivatives in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 للاسماء

-0.94

++]=

-0.69

ISTRATION

-0.67

CUSSION

-0.66

bestos

-0.66

Referanser

-0.66

spreis

-0.65

FOOTNOTES

-0.65

 anún

-0.65

Bronnen

-0.64

POSITIVE LOGITS

pace

0.82

 Squares

0.71

 Halloween

0.71

 Christmas

0.67

 squares

0.62

pages

0.61

squares

0.59

 European

0.56

évaluateur

0.56

Squares

0.56

Activations Density 0.149%

terms related to exposure and derivatives in a scientific context

No Comments

No Known Activations