INDEX

Explanations

references to dates, specifically related to February

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

 propOrder

-1.04

 estoppel

-0.81

EDEFAULT

-0.80

 ProtoMessage

-0.78

Sas

-0.77

Попис

-0.77

Rena

-0.77

 Rocca

-0.72

Locke

-0.72

DebuggerNonUser

-0.71

POSITIVE LOGITS

 February

1.67

Feb

1.52

 FEBRUARY

1.47

February

1.47

FEBRUARY

1.42

 Februar

1.40

Feb

1.34

FEB

1.30

 Februari

1.28

 februari

1.23

Activations Density 0.043%

references to dates, specifically related to February

No Comments

No Known Activations