INDEX

Explanations

parentheses and mathematical expressions

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

-0.79

↵↵

-0.60

↵

-0.51

-0.50

-0.43

</strong>

-0.41

PARATOR

-0.40

and

-0.36

Codice

-0.35

POSITIVE LOGITS

 Autorizaciones

0.97

 IBOutlet

0.97

 CreateTagHelper

0.96

IBOutlet

0.95

ьаж

0.94

uxxxx

0.93

 otomatig

0.93

Tembelea

0.92

Efq

0.90

ंदीखरीदारी

0.88

Activations Density 0.270%

parentheses and mathematical expressions

No Comments

No Known Activations