INDEX

Explanations

references to repeated actions or events, particularly in a context related to elections or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WireFormatLite

-0.79

setVerticalGroup

-0.65

 Signalez

-0.65

 ISNI

-0.62

ValueStyle

-0.61

 cherchés

-0.61

TagMode

-0.60

 InkWell

-0.56

featureID

-0.56

"?>

-0.56

POSITIVE LOGITS

 previous

4.08

previous

3.58

Previous

3.30

 Previous

3.29

 PREVIOUS

3.00

 previously

2.83

 earlier

2.82

 предыду

2.81

 past

2.73

Previously

2.67

Activations Density 1.244%

references to repeated actions or events, particularly in a context related to elections or assessments

No Comments

No Known Activations