INDEX

Explanations

terms related to adhesive materials, specifically masking tape

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

ագրություններ

-0.67

enumi

-0.66

HasForeignKey

-0.65

 CreateTagHelper

-0.58

 สู

-0.55

 pinulongan

-0.55

enumii

-0.54

dibles

-0.52

InSection

-0.51

TableField

-0.49

POSITIVE LOGITS

principalTable

0.55

transQ

0.52

 Stealth

0.52

expansion

0.50

 Scotch

0.48

ChildIndex

0.47

seeded

0.47

 expansion

0.47

glPopMatrix

0.46

tape

0.46

Activations Density 0.223%

terms related to adhesive materials, specifically masking tape

No Comments

No Known Activations