INDEX

Explanations

references to sections, articles, and publication details in legal and academic documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 '\\;'

-0.60

 ISNI

-0.55

}`);

-0.55

 Esau

-0.55

ณ์

-0.54

Dox

-0.52

ẵng

-0.52

atosis

-0.51

 Allociné

-0.50

geddon

-0.49

POSITIVE LOGITS

ngdoc

0.77

IntoConstraints

0.67

 GenerationType

0.60

 nakalista

0.57

 otomatig

0.55

 PublicKey

0.49

awtextra

0.49

tvguidetime

0.47

Здра

0.47

ConstraintMaker

0.46

Activations Density 0.682%

references to sections, articles, and publication details in legal and academic documents

No Comments

No Known Activations