INDEX

Explanations

phrases related to the start of events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.hook_mlp_out

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

Vidite

-0.81

 насељу

-0.75

 يتيمه

-0.73

MigrationBuilder

-0.70

entiary

-0.70

 NSCoder

-0.69

Personendaten

-0.69

 Reverso

-0.68

]='\

-0.67

 ProtoMessage

-0.66

POSITIVE LOGITS

序

0.42

 kỷ

0.39

hoeddwyd

0.38

 volume

0.37

 stock

0.37

pay

0.36

 know

0.36

 dieses

0.35

cre

0.35

 Agreg

0.35

Activations Density 0.026%

phrases related to the start of events or actions

No Comments

No Known Activations