INDEX

Explanations

references to cycles and cyclical processes

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

 carina

-0.73

 suprême

-0.72

metheus

-0.71

ullable

-0.69

Transkript

-0.69

 auricular

-0.69

 farina

-0.68

]);

-0.68

 Nathalie

-0.67

Nathalie

-0.67

POSITIVE LOGITS

 cycle

2.69

 cycles

2.47

 Cycle

2.46

 CYCLE

2.30

Cycle

2.25

cycle

2.23

 Cycles

2.17

cycles

2.07

Cycles

2.04

CYCLE

1.90

Activations Density 0.089%

references to cycles and cyclical processes

No Comments

No Known Activations