INDEX

Explanations

phrases related to requests for assistance or interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ffey

-0.49

cuer

-0.49

วย

-0.48

 WATSON

-0.47

tieg

-0.47

roth

-0.46

viola

-0.46

fog

-0.45

alele

-0.45

 PeEnEo

-0.45

POSITIVE LOGITS

ReusableCell

0.75



0.69

createCanvas

0.67

 ProtoMessage

0.67

principalColumn

0.67

CloseOperation

0.66

PyExc

0.65

 שוליים

0.64

ganu

0.63

 fieldNum

0.62

Activations Density 0.028%

phrases related to requests for assistance or interaction

No Comments

No Known Activations