INDEX

Explanations

references to scientific figures and citations

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

:✨

-0.90

EndGlobalSection

-0.75

vician

-0.74

TypedDataSet

-0.74

Desen

-0.74

حياته

-0.73

 Hartman

-0.72

RunWith

-0.72

 Rogers

-0.71

POSITIVE LOGITS

Ref

2.26

ref

2.26

ref

2.17

Ref

2.12

REF

1.85

REF

1.77

 useRef

1.57

Refs

1.53

 refs

1.51

refs

1.45

Activations Density 0.250%

references to scientific figures and citations

No Comments

No Known Activations