INDEX

Explanations

references to volumes and methodologies in academic contexts

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

StrictEqual

-0.51

 ivelany

-0.47

ange

-0.45

 naka

-0.45

 coni

-0.43

 CONCEP

-0.42

 caufe

-0.42

 cauſe

-0.41

 mato

-0.41

 ſch

-0.40

POSITIVE LOGITS

III

0.90

III

0.88

 VIII

0.84

XXX

0.83

XII

0.82

IV

0.82

VIII

0.80

VII

0.80

VII

0.78

Activations Density 0.392%

references to volumes and methodologies in academic contexts

No Comments

No Known Activations