INDEX

Explanations

negations or negative terms related to expectations or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-1.12

 initComponents

-0.75

PyExc

-0.58

setOpaque

-0.57

HostException

-0.54

 nahilalakip

-0.53

igts

-0.50

 يتيمه

-0.49

 AllMovie

-0.47

Varint

-0.47

POSITIVE LOGITS

&-

0.91

related

0.66

shaped

0.64

based

0.64

mindedness

0.64

=-=-=-=-

0.60

sized

0.58

like

0.58

oriented

0.57

minded

0.56

Activations Density 0.863%

negations or negative terms related to expectations or values

No Comments

No Known Activations